diff --git a/model-00001-of-00022.safetensors b/model-00001-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93147f1cde076966f28ebd1b99018e76cac5d038 --- /dev/null +++ b/model-00001-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce1f185830664b8aa64062546b31079ba20f721ee2d8a113424e35275c92ca0 +size 7730198080 diff --git a/model-00002-of-00022.safetensors b/model-00002-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ebebc2c6f1aa494c453cc9b0a7ee0825bf5dfcb7 --- /dev/null +++ b/model-00002-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c6bd5b046c214003dd6b1d7bfa4107280e6dd25bce005063389f34d18567ca +size 10737577896 diff --git a/model-00003-of-00022.safetensors b/model-00003-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..659afffc54df5a8adadc6b84a0ed3f153843fcce --- /dev/null +++ b/model-00003-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faafea2634ed6c6f505bbf20bd502dbbc5dcd140837477c9245857fef110437b +size 8590062440 diff --git a/model-00004-of-00022.safetensors b/model-00004-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..392f35309ce3a9080cfb34f37b943a02c81887a8 --- /dev/null +++ b/model-00004-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bf0776cd72a3553b03c6134d96332a2a2e930901f7ce2532ba15f42456399f +size 10737577896 diff --git a/model-00005-of-00022.safetensors b/model-00005-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0d5850dc27992ed5e68160a86aa86437fea0416 --- /dev/null +++ b/model-00005-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539925ca6f7217d37bf892cb645999dc816fa4a2b9dbf129f72c3d9d556e6382 +size 8590062440 diff --git a/model-00006-of-00022.safetensors b/model-00006-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e2ca362932affd75f0383b908156f6d5047c5f8 --- /dev/null +++ b/model-00006-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3fa8d3764b98af1db3f3a22ea7acd4888d998f0aae9f51b4d38865e9bdea5cb +size 10737577896 diff --git a/model-00007-of-00022.safetensors b/model-00007-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18615eca2a6dbfa3ff50eabe50652fec5e8f90f1 --- /dev/null +++ b/model-00007-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc9923b0fd1569b628256f9df9f8f93a5d788374e0a96c5c201901b1dac4107e +size 8590063208 diff --git a/model-00008-of-00022.safetensors b/model-00008-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc63441e40be56576f90c2de6b87df322709406a --- /dev/null +++ b/model-00008-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc4113b404d7e6de1ac37ca964f2f2b60f58e7fb8d88a86c37115e1cf4b60a0 +size 10737579176 diff --git a/model-00009-of-00022.safetensors b/model-00009-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a830785e35623694ae20faa4b17caeb01dd5bec --- /dev/null +++ b/model-00009-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9428654caef0b9dc00454dace3f2faade6ed53d029e88e4b3975652222f9fa66 +size 8590063464 diff --git a/model-00010-of-00022.safetensors b/model-00010-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5b7976365ed1cf8cbb0ade4851b87c5fb99d5ae --- /dev/null +++ b/model-00010-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2f3f10a6b62b6cc02a8706b8d6ace28d8ad580bc33538965a936ab9675038d +size 10737579176 diff --git a/model-00011-of-00022.safetensors b/model-00011-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d13d0fc330cb8c6a7992eebfa97f714c14bcd2b --- /dev/null +++ b/model-00011-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31854d08bf7c577034f1dcd20b8694b2224b10327f0bc13696a1c73a033a773 +size 10433766568 diff --git a/model-00012-of-00022.safetensors b/model-00012-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb8659f5df76dbdd07d276b920011729f38bb283 --- /dev/null +++ b/model-00012-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdc2c0fe4b65c7f1d2e8ed8fd23eb7130a70a118f07240d2469be380d08ca1fb +size 10737579176 diff --git a/model-00013-of-00022.safetensors b/model-00013-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9036d4855b4897491c832b512e158e88627c0096 --- /dev/null +++ b/model-00013-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:171b58ee1dc4467a5695875a07824c5b0400fa23099f7f2e9e7a6788014ef909 +size 8590063464 diff --git a/model-00014-of-00022.safetensors b/model-00014-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5ea8eee004c0ccc3742a3c38a412a6a50f4b22f --- /dev/null +++ b/model-00014-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16bab103ed0b7906648709032876f19db54f03af9280e8daa4aa337611401abd +size 10737579176 diff --git a/model-00015-of-00022.safetensors b/model-00015-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e2733e7516473315c39123eb616c4eedc61868d --- /dev/null +++ b/model-00015-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c945546a09e9c6054627d1f1a001f7942453bb15e5a9111e055cee26a136a18 +size 8590063464 diff --git a/model-00016-of-00022.safetensors b/model-00016-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb6e5d7093c090835c30a41fb29905f8be7a8ad1 --- /dev/null +++ b/model-00016-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc56fbac4e543403d5d4fe06271e02a6dc5de750c992b2ea225078679b2b28ba +size 10737579176 diff --git a/model-00017-of-00022.safetensors b/model-00017-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..812a048e492d9dc38c9e3287a1b467b96d62afcc --- /dev/null +++ b/model-00017-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c983f7daa4c4bab8289f6e74e52d7afcc7f695405d9062676192ca1bf4e16b45 +size 8590063464 diff --git a/model-00018-of-00022.safetensors b/model-00018-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69a108699f6ca432806d6e10e7fdcd233896d513 --- /dev/null +++ b/model-00018-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f692106b9b84959bdc142c4670fdd3d3bfea93f511aadb9812b0fa59986b281 +size 10737579176 diff --git a/model-00019-of-00022.safetensors b/model-00019-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ca5965b4f82170a0631b043bd66f301a2ada140 --- /dev/null +++ b/model-00019-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e361bad14ca30ba3301216efbe47a415344e22717b6356e1f6867b48db1b3c2 +size 8590063464 diff --git a/model-00020-of-00022.safetensors b/model-00020-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14d32f9ce31ae6d0a86639123a5210b33e81b19f --- /dev/null +++ b/model-00020-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b4c9c82c6492656b55af792c820a1f580724e7c9dd4cb9ba97f9d8cafc92247 +size 10737579176 diff --git a/model-00021-of-00022.safetensors b/model-00021-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10cbd825c22830c71f3fff0bcceb1f0405788221 --- /dev/null +++ b/model-00021-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c43ac9e6d916cc256e2eb1b0af960722f1fdc31bdfec9d53a972dff54d8f8a09 +size 10735455808 diff --git a/model-00022-of-00022.safetensors b/model-00022-of-00022.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d6014816157376d0ac6bbeecbedb6c2b11be1901 --- /dev/null +++ b/model-00022-of-00022.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76693daaf306bfbae4f27d4de0b6e147f27b7b12a9d09083e1f9d59759fdf4c9 +size 786742432 diff --git a/model.safetensors.index.json b/model.safetensors.index.json index 207e9be7383fa9a3dac9c622d3b3bc5686c4c0ee..cc92d4b8f3fb5f7ff62be514ee9f4aefb446231e 100644 --- a/model.safetensors.index.json +++ b/model.safetensors.index.json @@ -3,24166 +3,24166 @@ "total_size": 205779426304 }, "weight_map": { - "model.word_embeddings.weight": "model-00000-of-00016.safetensors", - "model.layers.0.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.0.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.0.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.0.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.0.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.0.mlp.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.0.mlp.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.1.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.1.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.1.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.1.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.1.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.1.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.1.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.1.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.1.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.1.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.1.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.1.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.2.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.2.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.2.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.2.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.2.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.2.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.2.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.2.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.2.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.2.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.2.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.2.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.3.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.3.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.3.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.3.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.3.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.3.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.3.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.3.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.3.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.3.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.3.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.3.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.4.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.4.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.4.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.4.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.4.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.4.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.4.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.4.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.4.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.4.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.4.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.4.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.5.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.5.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.5.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.5.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.5.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.5.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.5.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.5.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.5.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.5.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.5.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.5.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.6.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.6.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.6.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.6.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.6.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.6.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.6.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.6.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.6.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.6.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.6.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.6.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.7.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.7.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.7.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.7.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.7.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.7.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.7.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.7.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.7.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.7.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.7.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.7.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.8.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.8.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.8.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.8.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.8.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.8.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.8.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.8.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.8.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.8.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.8.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.8.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.9.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.9.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.9.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.9.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.9.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.9.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.9.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.9.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.9.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.9.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.9.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.9.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.10.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.10.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.10.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.10.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.10.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.10.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.10.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.10.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.10.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.10.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.10.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.10.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.11.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.11.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.11.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.11.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.11.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.11.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.11.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.11.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.11.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.11.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.11.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.11.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.12.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.12.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.12.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.12.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.12.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.12.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.12.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.12.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.12.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.12.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.12.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.12.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.13.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.13.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.13.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.13.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.13.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.13.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.13.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.13.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.13.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.13.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.13.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.13.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.14.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.14.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.14.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.14.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.14.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.14.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.14.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.14.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.14.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.14.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.14.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.14.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.attention.dense.weight": "model-00000-of-00016.safetensors", - "model.layers.15.attention.key_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.15.attention.query_key_value.weight": "model-00000-of-00016.safetensors", - "model.layers.15.attention.query_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.15.input_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.gate.expert_bias": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.gate.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.0.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.0.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.1.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.1.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.2.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.2.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.3.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.3.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.4.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.4.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.5.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.5.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.6.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.6.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.7.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.7.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.8.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.8.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.9.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.9.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.10.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.10.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.11.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.11.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.12.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.12.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.13.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.13.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.14.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.14.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.15.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.15.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.16.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.16.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.17.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.17.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.18.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.18.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.19.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.19.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.20.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.20.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.21.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.21.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.22.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.22.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.23.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.23.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.24.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.24.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.25.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.25.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.26.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.26.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.27.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.27.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.28.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.28.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.29.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.29.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.30.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.30.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.31.down_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.31.up_proj.weight": "model-00000-of-00016.safetensors", - "model.layers.15.mlp.experts.32.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.32.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.33.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.33.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.34.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.34.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.35.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.35.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.36.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.36.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.37.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.37.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.38.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.38.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.39.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.39.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.40.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.40.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.41.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.41.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.42.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.42.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.43.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.43.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.44.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.44.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.45.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.45.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.46.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.46.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.47.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.47.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.48.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.48.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.49.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.49.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.50.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.50.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.51.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.51.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.52.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.52.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.53.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.53.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.54.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.54.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.55.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.55.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.56.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.56.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.57.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.57.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.58.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.58.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.59.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.59.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.60.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.60.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.61.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.61.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.62.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.62.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.63.down_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.63.up_proj.weight": "model-00001-of-00016.safetensors", - "model.layers.15.mlp.experts.64.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.64.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.65.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.65.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.66.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.66.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.67.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.67.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.68.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.68.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.69.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.69.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.70.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.70.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.71.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.71.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.72.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.72.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.73.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.73.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.74.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.74.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.75.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.75.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.76.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.76.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.77.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.77.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.78.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.78.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.79.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.79.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.80.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.80.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.81.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.81.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.82.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.82.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.83.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.83.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.84.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.84.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.85.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.85.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.86.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.86.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.87.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.87.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.88.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.88.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.89.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.89.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.90.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.90.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.91.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.91.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.92.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.92.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.93.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.93.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.94.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.94.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.95.down_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.95.up_proj.weight": "model-00002-of-00016.safetensors", - "model.layers.15.mlp.experts.96.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.96.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.97.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.97.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.98.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.98.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.99.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.99.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.100.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.100.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.101.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.101.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.102.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.102.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.103.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.103.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.104.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.104.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.105.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.105.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.106.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.106.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.107.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.107.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.108.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.108.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.109.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.109.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.110.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.110.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.111.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.111.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.112.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.112.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.113.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.113.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.114.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.114.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.115.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.115.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.116.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.116.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.117.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.117.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.118.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.118.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.119.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.119.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.120.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.120.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.121.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.121.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.122.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.122.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.123.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.123.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.124.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.124.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.125.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.125.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.126.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.126.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.127.down_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.127.up_proj.weight": "model-00003-of-00016.safetensors", - "model.layers.15.mlp.experts.128.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.128.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.128.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.129.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.129.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.129.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.130.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.130.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.130.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.131.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.131.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.131.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.132.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.132.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.132.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.133.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.133.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.133.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.134.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.134.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.134.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.135.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.135.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.135.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.136.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.136.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.136.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.137.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.137.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.137.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.138.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.138.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.138.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.139.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.139.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.139.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.140.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.140.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.140.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.141.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.141.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.141.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.142.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.142.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.142.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.143.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.143.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.143.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.144.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.144.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.144.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.145.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.145.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.145.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.146.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.146.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.146.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.147.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.147.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.147.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.148.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.148.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.148.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.149.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.149.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.149.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.150.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.150.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.150.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.151.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.151.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.151.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.152.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.152.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.152.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.153.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.153.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.153.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.154.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.154.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.154.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.155.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.155.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.155.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.156.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.156.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.156.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.157.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.157.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.157.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.158.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.158.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.158.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.159.down_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.159.gate_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.159.up_proj.weight": "model-00004-of-00016.safetensors", - "model.layers.15.mlp.experts.160.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.160.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.160.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.161.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.161.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.161.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.162.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.162.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.162.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.163.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.163.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.163.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.164.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.164.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.164.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.165.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.165.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.165.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.166.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.166.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.166.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.167.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.167.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.167.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.168.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.168.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.168.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.169.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.169.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.169.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.170.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.170.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.170.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.171.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.171.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.171.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.172.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.172.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.172.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.173.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.173.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.173.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.174.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.174.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.174.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.175.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.175.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.175.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.176.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.176.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.176.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.177.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.177.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.177.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.178.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.178.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.178.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.179.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.179.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.179.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.180.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.180.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.180.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.181.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.181.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.181.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.182.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.182.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.182.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.183.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.183.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.183.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.184.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.184.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.184.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.185.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.185.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.185.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.186.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.186.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.186.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.187.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.187.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.187.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.188.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.188.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.188.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.189.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.189.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.189.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.190.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.190.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.190.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.191.down_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.191.gate_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.191.up_proj.weight": "model-00005-of-00016.safetensors", - "model.layers.15.mlp.experts.192.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.192.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.192.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.193.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.193.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.193.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.194.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.194.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.194.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.195.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.195.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.195.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.196.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.196.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.196.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.197.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.197.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.197.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.198.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.198.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.198.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.199.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.199.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.199.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.200.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.200.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.200.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.201.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.201.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.201.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.202.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.202.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.202.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.203.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.203.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.203.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.204.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.204.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.204.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.205.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.205.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.205.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.206.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.206.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.206.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.207.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.207.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.207.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.208.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.208.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.208.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.209.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.209.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.209.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.210.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.210.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.210.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.211.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.211.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.211.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.212.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.212.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.212.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.213.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.213.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.213.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.214.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.214.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.214.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.215.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.215.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.215.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.216.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.216.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.216.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.217.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.217.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.217.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.218.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.218.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.218.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.219.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.219.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.219.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.220.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.220.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.220.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.221.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.221.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.221.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.222.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.222.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.222.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.223.down_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.223.gate_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.223.up_proj.weight": "model-00006-of-00016.safetensors", - "model.layers.15.mlp.experts.224.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.224.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.224.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.225.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.225.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.225.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.226.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.226.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.226.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.227.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.227.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.227.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.228.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.228.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.228.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.229.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.229.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.229.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.230.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.230.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.230.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.231.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.231.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.231.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.232.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.232.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.232.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.233.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.233.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.233.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.234.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.234.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.234.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.235.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.235.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.235.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.236.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.236.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.236.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.237.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.237.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.237.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.238.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.238.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.238.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.239.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.239.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.239.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.240.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.240.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.240.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.241.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.241.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.241.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.242.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.242.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.242.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.243.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.243.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.243.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.244.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.244.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.244.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.245.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.245.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.245.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.246.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.246.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.246.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.247.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.247.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.247.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.248.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.248.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.248.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.249.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.249.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.249.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.250.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.250.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.250.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.251.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.251.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.251.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.252.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.252.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.252.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.253.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.253.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.253.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.254.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.254.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.254.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.255.down_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.255.gate_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.15.mlp.experts.255.up_proj.weight": "model-00007-of-00016.safetensors", - "model.layers.16.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.16.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.16.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.16.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.16.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.16.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.16.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.16.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.16.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.16.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.16.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.16.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.16.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.17.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.17.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.17.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.17.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.17.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.17.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.17.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.17.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.17.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.17.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.17.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.17.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.18.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.18.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.18.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.18.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.18.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.18.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.18.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.18.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.18.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.18.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.18.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.18.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.19.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.19.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.19.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.19.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.19.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.19.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.19.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.19.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.19.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.19.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.19.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.19.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.20.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.20.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.20.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.20.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.20.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.20.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.20.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.20.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.20.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.20.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.20.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.20.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.21.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.21.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.21.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.21.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.21.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.21.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.21.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.21.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.21.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.21.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.21.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.21.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.22.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.22.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.22.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.22.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.22.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.22.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.22.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.22.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.22.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.22.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.22.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.22.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.23.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.23.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.23.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.23.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.23.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.23.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.23.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.23.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.23.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.23.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.23.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.23.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.24.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.24.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.24.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.24.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.24.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.24.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.24.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.24.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.24.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.24.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.24.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.24.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.25.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.25.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.25.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.25.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.25.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.25.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.25.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.25.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.25.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.25.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.25.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.25.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.26.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.26.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.26.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.26.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.26.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.26.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.26.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.26.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.26.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.26.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.26.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.26.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.27.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.27.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.27.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.27.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.27.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.27.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.27.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.27.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.27.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.27.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.27.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.27.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.28.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.28.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.28.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.28.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.28.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.28.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.28.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.28.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.28.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.28.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.28.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.28.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.29.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.29.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.29.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.29.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.29.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.29.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.29.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.29.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.29.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.29.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.29.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.29.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.30.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.30.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.30.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.30.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.30.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.30.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.30.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.30.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.30.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.30.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.30.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.30.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.attention.dense.weight": "model-00008-of-00016.safetensors", - "model.layers.31.attention.key_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.31.attention.query_key_value.weight": "model-00008-of-00016.safetensors", - "model.layers.31.attention.query_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.31.input_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.gate.expert_bias": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.gate.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.0.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.0.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.1.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.1.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.2.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.2.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.3.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.3.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.4.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.4.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.5.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.5.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.6.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.6.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.7.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.7.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.8.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.8.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.9.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.9.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.10.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.10.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.11.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.11.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.12.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.12.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.13.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.13.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.14.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.14.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.15.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.15.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.16.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.16.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.17.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.17.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.18.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.18.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.19.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.19.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.20.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.20.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.21.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.21.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.22.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.22.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.23.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.23.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.24.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.24.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.25.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.25.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.26.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.26.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.27.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.27.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.28.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.28.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.29.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.29.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.30.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.30.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.31.down_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.31.up_proj.weight": "model-00008-of-00016.safetensors", - "model.layers.31.mlp.experts.32.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.32.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.33.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.33.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.34.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.34.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.35.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.35.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.36.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.36.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.37.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.37.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.38.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.38.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.39.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.39.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.40.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.40.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.41.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.41.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.42.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.42.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.43.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.43.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.44.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.44.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.45.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.45.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.46.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.46.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.47.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.47.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.48.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.48.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.49.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.49.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.50.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.50.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.51.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.51.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.52.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.52.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.53.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.53.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.54.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.54.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.55.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.55.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.56.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.56.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.57.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.57.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.58.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.58.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.59.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.59.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.60.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.60.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.61.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.61.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.62.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.62.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.63.down_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.63.up_proj.weight": "model-00009-of-00016.safetensors", - "model.layers.31.mlp.experts.64.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.64.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.65.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.65.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.66.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.66.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.67.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.67.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.68.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.68.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.69.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.69.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.70.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.70.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.71.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.71.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.72.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.72.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.73.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.73.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.74.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.74.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.75.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.75.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.76.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.76.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.77.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.77.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.78.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.78.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.79.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.79.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.80.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.80.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.81.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.81.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.82.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.82.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.83.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.83.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.84.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.84.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.85.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.85.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.86.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.86.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.87.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.87.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.88.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.88.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.89.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.89.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.90.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.90.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.91.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.91.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.92.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.92.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.93.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.93.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.94.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.94.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.95.down_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.95.up_proj.weight": "model-00010-of-00016.safetensors", - "model.layers.31.mlp.experts.96.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.96.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.97.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.97.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.98.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.98.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.99.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.99.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.100.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.100.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.101.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.101.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.102.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.102.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.103.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.103.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.104.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.104.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.105.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.105.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.106.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.106.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.107.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.107.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.108.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.108.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.109.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.109.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.110.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.110.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.111.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.111.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.112.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.112.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.113.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.113.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.114.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.114.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.115.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.115.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.116.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.116.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.117.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.117.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.118.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.118.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.119.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.119.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.120.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.120.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.121.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.121.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.122.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.122.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.123.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.123.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.124.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.124.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.125.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.125.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.126.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.126.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.127.down_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.127.up_proj.weight": "model-00011-of-00016.safetensors", - "model.layers.31.mlp.experts.128.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.128.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.128.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.129.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.129.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.129.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.130.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.130.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.130.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.131.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.131.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.131.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.132.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.132.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.132.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.133.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.133.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.133.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.134.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.134.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.134.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.135.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.135.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.135.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.136.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.136.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.136.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.137.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.137.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.137.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.138.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.138.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.138.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.139.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.139.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.139.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.140.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.140.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.140.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.141.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.141.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.141.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.142.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.142.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.142.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.143.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.143.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.143.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.144.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.144.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.144.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.145.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.145.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.145.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.146.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.146.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.146.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.147.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.147.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.147.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.148.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.148.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.148.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.149.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.149.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.149.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.150.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.150.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.150.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.151.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.151.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.151.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.152.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.152.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.152.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.153.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.153.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.153.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.154.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.154.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.154.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.155.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.155.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.155.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.156.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.156.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.156.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.157.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.157.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.157.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.158.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.158.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.158.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.159.down_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.159.gate_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.159.up_proj.weight": "model-00012-of-00016.safetensors", - "model.layers.31.mlp.experts.160.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.160.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.160.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.161.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.161.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.161.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.162.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.162.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.162.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.163.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.163.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.163.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.164.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.164.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.164.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.165.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.165.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.165.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.166.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.166.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.166.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.167.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.167.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.167.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.168.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.168.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.168.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.169.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.169.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.169.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.170.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.170.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.170.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.171.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.171.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.171.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.172.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.172.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.172.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.173.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.173.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.173.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.174.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.174.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.174.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.175.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.175.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.175.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.176.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.176.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.176.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.177.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.177.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.177.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.178.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.178.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.178.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.179.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.179.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.179.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.180.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.180.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.180.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.181.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.181.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.181.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.182.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.182.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.182.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.183.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.183.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.183.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.184.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.184.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.184.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.185.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.185.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.185.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.186.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.186.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.186.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.187.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.187.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.187.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.188.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.188.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.188.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.189.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.189.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.189.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.190.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.190.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.190.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.191.down_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.191.gate_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.191.up_proj.weight": "model-00013-of-00016.safetensors", - "model.layers.31.mlp.experts.192.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.192.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.192.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.193.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.193.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.193.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.194.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.194.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.194.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.195.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.195.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.195.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.196.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.196.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.196.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.197.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.197.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.197.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.198.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.198.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.198.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.199.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.199.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.199.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.200.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.200.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.200.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.201.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.201.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.201.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.202.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.202.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.202.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.203.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.203.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.203.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.204.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.204.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.204.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.205.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.205.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.205.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.206.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.206.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.206.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.207.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.207.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.207.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.208.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.208.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.208.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.209.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.209.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.209.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.210.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.210.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.210.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.211.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.211.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.211.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.212.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.212.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.212.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.213.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.213.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.213.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.214.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.214.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.214.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.215.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.215.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.215.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.216.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.216.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.216.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.217.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.217.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.217.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.218.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.218.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.218.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.219.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.219.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.219.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.220.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.220.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.220.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.221.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.221.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.221.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.222.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.222.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.222.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.223.down_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.223.gate_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.223.up_proj.weight": "model-00014-of-00016.safetensors", - "model.layers.31.mlp.experts.224.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.224.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.224.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.225.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.225.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.225.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.226.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.226.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.226.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.227.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.227.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.227.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.228.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.228.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.228.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.229.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.229.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.229.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.230.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.230.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.230.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.231.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.231.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.231.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.232.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.232.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.232.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.233.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.233.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.233.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.234.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.234.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.234.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.235.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.235.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.235.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.236.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.236.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.236.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.237.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.237.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.237.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.238.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.238.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.238.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.239.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.239.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.239.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.240.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.240.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.240.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.241.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.241.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.241.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.242.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.242.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.242.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.243.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.243.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.243.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.244.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.244.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.244.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.245.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.245.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.245.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.246.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.246.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.246.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.247.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.247.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.247.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.248.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.248.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.248.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.249.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.249.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.249.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.250.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.250.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.250.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.251.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.251.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.251.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.252.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.252.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.252.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.253.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.253.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.253.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.254.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.254.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.254.up_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.255.down_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.255.gate_proj.weight": "model-00015-of-00016.safetensors", - "model.layers.31.mlp.experts.255.up_proj.weight": "model-00015-of-00016.safetensors", - "lm_head.weight": "model-00008-of-00016.safetensors", - "model.norm.weight": "model-00008-of-00016.safetensors" + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.64.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.65.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.66.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.67.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.68.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.69.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.70.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.71.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.72.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.73.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.74.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.75.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.76.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.77.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.78.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.79.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.80.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.81.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.82.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.83.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.84.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.85.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.86.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.87.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.88.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.89.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.90.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.91.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.92.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.93.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.94.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.95.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.96.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.97.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.98.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.99.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.100.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.101.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.102.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.103.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.104.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.105.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.106.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.107.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.108.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.109.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.110.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.111.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.112.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.113.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.114.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.115.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.116.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.117.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.118.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.119.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.120.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.121.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.122.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.123.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.124.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.125.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.126.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.127.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.128.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.129.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.130.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.131.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.132.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.133.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.134.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.135.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.136.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.137.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.138.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.139.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.140.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.141.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.142.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.143.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.144.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.145.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.146.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.147.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.148.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.149.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.150.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.151.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.152.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.153.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.154.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.155.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.156.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.157.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.158.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.159.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.160.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.161.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.162.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.163.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.164.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.165.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.166.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.167.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.168.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.169.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.170.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.171.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.172.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.173.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.174.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.175.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.176.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.177.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.178.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.179.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.180.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.181.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.182.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.183.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.184.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.185.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.186.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.187.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.188.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.189.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.190.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.191.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.192.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.193.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.194.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.195.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.196.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.197.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.198.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.199.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.200.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.201.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.202.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.203.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.204.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.205.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.206.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.207.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.208.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.209.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.210.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.211.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.212.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.213.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.214.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.215.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.216.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.217.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.218.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.219.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.220.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.221.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.222.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.223.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.224.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.225.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.226.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.227.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.228.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.229.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.230.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.231.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.232.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.233.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.234.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.235.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.236.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.237.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.238.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.239.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.240.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.241.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.242.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.243.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.244.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.245.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.246.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.247.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.248.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.249.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.250.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.251.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.252.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.253.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.254.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.255.down_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.64.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.65.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.66.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.67.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.68.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.69.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.70.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.71.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.72.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.73.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.74.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.75.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.76.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.77.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.78.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.79.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.80.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.81.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.82.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.83.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.84.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.85.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.86.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.87.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.88.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.89.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.90.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.91.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.92.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.93.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.94.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.95.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.96.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.97.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.98.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.99.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.100.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.101.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.102.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.103.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.104.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.105.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.106.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.107.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.108.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.109.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.110.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.111.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.112.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.113.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.114.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.115.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.116.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.117.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.118.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.119.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.120.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.121.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.122.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.123.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.124.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.125.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.126.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.127.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.128.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.128.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.129.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.129.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.130.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.130.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.131.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.131.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.132.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.132.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.133.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.133.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.134.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.134.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.135.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.135.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.136.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.136.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.137.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.137.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.138.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.138.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.139.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.139.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.140.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.140.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.141.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.141.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.142.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.142.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.143.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.143.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.144.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.144.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.145.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.145.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.146.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.146.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.147.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.147.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.148.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.148.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.149.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.149.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.150.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.150.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.151.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.151.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.152.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.152.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.153.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.153.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.154.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.154.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.155.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.155.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.156.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.156.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.157.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.157.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.158.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.158.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.159.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.159.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.160.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.160.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.161.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.161.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.162.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.162.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.163.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.163.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.164.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.164.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.165.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.165.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.166.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.166.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.167.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.167.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.168.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.168.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.169.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.169.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.170.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.170.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.171.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.171.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.172.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.172.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.173.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.173.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.174.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.174.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.175.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.175.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.176.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.176.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.177.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.177.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.178.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.178.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.179.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.179.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.180.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.180.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.181.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.181.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.182.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.182.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.183.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.183.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.184.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.184.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.185.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.185.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.186.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.186.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.187.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.187.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.188.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.188.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.189.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.189.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.190.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.190.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.191.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.191.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.192.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.192.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.193.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.193.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.194.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.194.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.195.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.195.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.196.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.196.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.197.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.197.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.198.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.198.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.199.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.199.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.200.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.200.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.201.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.201.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.202.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.202.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.203.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.203.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.204.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.204.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.205.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.205.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.206.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.206.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.207.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.207.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.208.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.208.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.209.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.209.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.210.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.210.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.211.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.211.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.212.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.212.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.213.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.213.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.214.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.214.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.215.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.215.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.216.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.216.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.217.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.217.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.218.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.218.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.219.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.219.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.220.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.220.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.221.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.221.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.222.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.222.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.223.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.223.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.224.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.224.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.225.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.225.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.226.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.226.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.227.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.227.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.228.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.228.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.229.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.229.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.230.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.230.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.231.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.231.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.232.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.232.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.233.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.233.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.234.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.234.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.235.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.235.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.236.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.236.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.237.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.237.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.238.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.238.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.239.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.239.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.240.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.240.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.241.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.241.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.242.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.242.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.243.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.243.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.244.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.244.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.245.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.245.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.246.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.246.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.247.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.247.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.248.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.248.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.249.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.249.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.250.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.250.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.251.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.251.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.252.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.252.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.253.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.253.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.254.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.254.up_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.255.gate_proj.weight": "model-00001-of-00022.safetensors", + "model.layers.1.mlp.experts.255.up_proj.weight": "model-00001-of-00022.safetensors", + "model.word_embeddings.weight": "model-00001-of-00022.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.64.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.65.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.66.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.67.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.68.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.69.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.70.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.71.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.72.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.73.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.74.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.75.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.76.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.77.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.78.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.79.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.80.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.81.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.82.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.83.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.84.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.85.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.86.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.87.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.88.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.89.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.90.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.91.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.92.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.93.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.94.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.95.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.96.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.97.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.98.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.99.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.100.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.101.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.102.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.103.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.104.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.105.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.106.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.107.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.108.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.109.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.110.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.111.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.112.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.113.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.114.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.115.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.116.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.117.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.118.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.119.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.120.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.121.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.122.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.123.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.124.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.125.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.126.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.127.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.128.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.128.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.129.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.129.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.130.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.130.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.131.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.131.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.132.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.132.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.133.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.133.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.134.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.134.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.135.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.135.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.136.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.136.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.137.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.137.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.138.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.138.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.139.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.139.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.140.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.140.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.141.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.141.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.142.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.142.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.143.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.143.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.144.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.144.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.145.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.145.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.146.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.146.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.147.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.147.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.148.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.148.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.149.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.149.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.150.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.150.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.151.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.151.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.152.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.152.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.153.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.153.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.154.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.154.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.155.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.155.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.156.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.156.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.157.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.157.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.158.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.158.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.159.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.159.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.160.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.160.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.161.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.161.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.162.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.162.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.163.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.163.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.164.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.164.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.165.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.165.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.166.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.166.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.167.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.167.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.168.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.168.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.169.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.169.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.170.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.170.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.171.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.171.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.172.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.172.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.173.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.173.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.174.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.174.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.175.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.175.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.176.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.176.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.177.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.177.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.178.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.178.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.179.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.179.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.180.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.180.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.181.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.181.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.182.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.182.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.183.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.183.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.184.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.184.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.185.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.185.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.186.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.186.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.187.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.187.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.188.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.188.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.189.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.189.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.190.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.190.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.191.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.191.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.192.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.192.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.193.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.193.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.194.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.194.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.195.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.195.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.196.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.196.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.197.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.197.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.198.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.198.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.199.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.199.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.200.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.200.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.201.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.201.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.202.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.202.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.203.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.203.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.204.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.204.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.205.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.205.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.206.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.206.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.207.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.207.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.208.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.208.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.209.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.209.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.210.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.210.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.211.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.211.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.212.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.212.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.213.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.213.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.214.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.214.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.215.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.215.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.216.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.216.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.217.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.217.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.218.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.218.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.219.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.219.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.220.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.220.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.221.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.221.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.222.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.222.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.223.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.223.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.224.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.224.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.225.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.225.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.226.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.226.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.227.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.227.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.228.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.228.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.229.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.229.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.230.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.230.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.231.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.231.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.232.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.232.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.233.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.233.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.234.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.234.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.235.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.235.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.236.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.236.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.237.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.237.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.238.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.238.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.239.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.239.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.240.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.240.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.241.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.241.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.242.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.242.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.243.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.243.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.244.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.244.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.245.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.245.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.246.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.246.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.247.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.247.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.248.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.248.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.249.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.249.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.250.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.250.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.251.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.251.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.252.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.252.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.253.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.253.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.254.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.254.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.255.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.255.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.128.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.128.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.129.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.129.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.130.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.130.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.131.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.131.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.132.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.132.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.133.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.133.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.134.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.134.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.135.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.135.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.136.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.136.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.137.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.137.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.138.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.138.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.139.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.139.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.140.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.140.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.141.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.141.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.142.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.142.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.143.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.143.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.144.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.144.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.145.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.145.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.146.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.146.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.147.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.147.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.148.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.148.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.149.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.149.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.150.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.150.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.151.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.151.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.152.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.152.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.153.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.153.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.154.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.154.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.155.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.155.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.156.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.156.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.157.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.157.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.158.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.158.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.159.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.159.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.160.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.160.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.161.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.161.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.162.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.162.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.163.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.163.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.164.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.164.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.165.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.165.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.166.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.166.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.167.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.167.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.168.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.168.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.169.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.169.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.170.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.170.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.171.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.171.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.172.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.172.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.173.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.173.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.174.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.174.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.175.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.175.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.176.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.176.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.177.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.177.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.178.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.178.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.179.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.179.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.180.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.180.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.181.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.181.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.182.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.182.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.183.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.183.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.184.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.184.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.185.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.185.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.186.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.186.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.187.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.187.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.188.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.188.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.189.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.189.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.190.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.190.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.191.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.191.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.192.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.192.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.193.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.193.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.194.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.194.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.195.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.195.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.196.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.196.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.197.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.197.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.198.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.198.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.199.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.199.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.200.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.200.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.201.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.201.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.202.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.202.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.203.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.203.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.204.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.204.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.205.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.205.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.206.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.206.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.207.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.207.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.208.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.208.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.209.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.209.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.210.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.210.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.211.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.211.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.212.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.212.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.213.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.213.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.214.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.214.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.215.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.215.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.216.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.216.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.217.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.217.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.218.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.218.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.219.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.219.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.220.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.220.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.221.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.221.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.222.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.222.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.223.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.223.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.224.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.224.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.225.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.225.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.226.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.226.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.227.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.227.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.228.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.228.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.229.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.229.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.230.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.230.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.231.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.231.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.232.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.232.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.233.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.233.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.234.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.234.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.235.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.235.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.236.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.236.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.237.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.237.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.238.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.238.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.239.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.239.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.240.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.240.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.241.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.241.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.242.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.242.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.243.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.243.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.244.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.244.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.245.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.245.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.246.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.246.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.247.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.247.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.248.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.248.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.249.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.249.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.250.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.250.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.251.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.251.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.252.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.252.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.253.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.253.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.254.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.254.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.255.gate_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.3.mlp.experts.255.up_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.64.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.65.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.66.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.67.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.68.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.69.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.70.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.71.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.72.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.73.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.74.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.75.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.76.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.77.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.78.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.79.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.80.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.81.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.82.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.83.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.84.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.85.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.86.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.87.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.88.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.89.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.90.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.91.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.92.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.93.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.94.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.95.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.96.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.97.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.98.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.99.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.100.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.101.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.102.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.103.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.104.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.105.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.106.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.107.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.108.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.109.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.110.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.111.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.112.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.113.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.114.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.115.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.116.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.117.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.118.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.119.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.120.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.121.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.122.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.123.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.124.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.125.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.126.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.127.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.128.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.129.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.130.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.131.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.132.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.133.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.134.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.135.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.136.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.137.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.138.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.139.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.140.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.141.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.142.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.143.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.144.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.145.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.146.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.147.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.148.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.149.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.150.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.151.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.152.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.153.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.154.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.155.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.156.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.157.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.158.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.159.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.160.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.161.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.162.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.163.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.164.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.165.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.166.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.167.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.168.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.169.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.170.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.171.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.172.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.173.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.174.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.175.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.176.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.177.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.178.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.179.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.180.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.181.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.182.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.183.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.184.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.185.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.186.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.187.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.188.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.189.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.190.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.191.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.192.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.193.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.194.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.195.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.196.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.197.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.198.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.199.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.200.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.201.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.202.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.203.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.204.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.205.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.206.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.207.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.208.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.209.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.210.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.211.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.212.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.213.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.214.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.215.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.216.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.217.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.218.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.219.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.220.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.221.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.222.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.223.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.224.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.225.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.226.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.227.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.228.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.229.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.230.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.231.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.232.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.233.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.234.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.235.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.236.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.237.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.238.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.239.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.240.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.241.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.242.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.243.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.244.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.245.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.246.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.247.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.248.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.249.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.250.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.251.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.252.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.253.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.254.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.2.mlp.experts.255.down_proj.weight": "model-00002-of-00022.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.128.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.129.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.130.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.131.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.132.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.133.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.134.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.135.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.136.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.137.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.138.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.139.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.140.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.141.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.142.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.143.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.144.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.145.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.146.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.147.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.148.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.149.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.150.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.151.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.152.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.153.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.154.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.155.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.156.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.157.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.158.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.159.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.160.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.161.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.162.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.163.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.164.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.165.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.166.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.167.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.168.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.169.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.170.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.171.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.172.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.173.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.174.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.175.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.176.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.177.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.178.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.179.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.180.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.181.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.182.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.183.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.184.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.185.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.186.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.187.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.188.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.189.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.190.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.191.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.192.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.193.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.194.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.195.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.196.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.197.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.198.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.199.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.200.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.201.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.202.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.203.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.204.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.205.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.206.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.207.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.208.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.209.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.210.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.211.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.212.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.213.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.214.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.215.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.216.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.217.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.218.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.219.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.220.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.221.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.222.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.223.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.224.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.225.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.226.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.227.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.228.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.229.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.230.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.231.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.232.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.233.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.234.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.235.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.236.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.237.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.238.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.239.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.240.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.241.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.242.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.243.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.244.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.245.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.246.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.247.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.248.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.249.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.250.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.251.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.252.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.253.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.254.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.255.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.128.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.129.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.130.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.131.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.132.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.133.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.134.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.135.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.136.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.137.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.138.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.139.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.140.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.141.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.142.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.143.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.144.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.145.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.146.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.147.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.148.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.149.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.150.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.151.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.152.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.153.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.154.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.155.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.156.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.157.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.158.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.159.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.160.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.161.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.162.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.163.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.164.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.165.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.166.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.167.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.168.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.169.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.170.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.171.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.172.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.173.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.174.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.175.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.176.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.177.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.178.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.179.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.180.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.181.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.182.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.183.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.184.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.185.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.186.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.187.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.188.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.189.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.190.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.191.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.192.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.193.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.194.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.195.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.196.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.197.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.198.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.199.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.200.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.201.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.202.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.203.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.204.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.205.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.206.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.207.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.208.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.209.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.210.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.211.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.212.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.213.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.214.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.215.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.216.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.217.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.218.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.219.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.220.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.221.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.222.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.223.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.224.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.225.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.226.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.227.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.228.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.229.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.230.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.231.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.232.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.233.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.234.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.235.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.236.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.237.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.238.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.239.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.240.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.241.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.242.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.243.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.244.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.245.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.246.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.247.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.248.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.249.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.250.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.251.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.252.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.253.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.254.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.3.mlp.experts.255.down_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.128.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.128.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.129.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.129.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.130.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.130.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.131.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.131.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.132.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.132.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.133.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.133.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.134.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.134.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.135.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.135.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.136.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.136.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.137.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.137.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.138.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.138.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.139.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.139.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.140.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.140.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.141.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.141.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.142.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.142.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.143.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.143.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.144.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.144.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.145.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.145.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.146.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.146.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.147.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.147.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.148.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.148.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.149.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.149.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.150.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.150.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.151.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.151.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.152.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.152.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.153.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.153.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.154.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.154.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.155.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.155.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.156.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.156.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.157.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.157.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.158.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.158.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.159.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.159.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.160.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.160.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.161.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.161.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.162.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.162.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.163.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.163.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.164.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.164.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.165.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.165.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.166.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.166.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.167.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.167.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.168.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.168.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.169.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.169.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.170.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.170.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.171.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.171.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.172.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.172.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.173.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.173.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.174.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.174.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.175.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.175.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.176.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.176.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.177.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.177.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.178.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.178.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.179.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.179.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.180.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.180.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.181.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.181.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.182.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.182.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.183.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.183.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.184.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.184.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.185.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.185.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.186.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.186.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.187.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.187.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.188.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.188.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.189.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.189.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.190.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.190.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.191.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.191.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.192.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.192.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.193.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.193.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.194.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.194.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.195.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.195.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.196.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.196.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.197.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.197.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.198.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.198.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.199.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.199.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.200.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.200.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.201.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.201.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.202.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.202.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.203.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.203.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.204.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.204.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.205.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.205.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.206.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.206.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.207.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.207.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.208.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.208.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.209.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.209.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.210.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.210.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.211.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.211.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.212.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.212.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.213.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.213.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.214.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.214.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.215.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.215.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.216.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.216.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.217.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.217.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.218.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.218.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.219.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.219.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.220.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.220.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.221.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.221.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.222.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.222.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.223.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.223.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.224.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.224.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.225.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.225.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.226.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.226.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.227.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.227.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.228.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.228.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.229.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.229.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.230.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.230.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.231.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.231.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.232.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.232.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.233.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.233.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.234.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.234.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.235.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.235.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.236.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.236.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.237.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.237.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.238.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.238.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.239.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.239.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.240.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.240.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.241.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.241.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.242.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.242.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.243.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.243.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.244.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.244.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.245.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.245.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.246.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.246.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.247.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.247.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.248.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.248.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.249.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.249.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.250.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.250.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.251.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.251.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.252.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.252.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.253.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.253.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.254.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.254.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.255.gate_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.4.mlp.experts.255.up_proj.weight": "model-00003-of-00022.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.128.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.129.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.130.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.131.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.132.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.133.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.134.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.135.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.136.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.137.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.138.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.139.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.140.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.141.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.142.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.143.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.144.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.145.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.146.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.147.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.148.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.149.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.150.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.151.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.152.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.153.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.154.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.155.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.156.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.157.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.158.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.159.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.160.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.161.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.162.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.163.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.164.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.165.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.166.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.167.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.168.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.169.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.170.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.171.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.172.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.173.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.174.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.175.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.176.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.177.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.178.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.179.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.180.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.181.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.182.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.183.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.184.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.185.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.186.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.187.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.188.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.189.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.190.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.191.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.192.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.193.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.194.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.195.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.196.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.197.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.198.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.199.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.200.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.201.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.202.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.203.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.204.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.205.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.206.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.207.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.208.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.209.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.210.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.211.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.212.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.213.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.214.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.215.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.216.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.217.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.218.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.219.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.220.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.221.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.222.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.223.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.224.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.225.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.226.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.227.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.228.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.229.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.230.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.231.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.232.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.233.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.234.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.235.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.236.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.237.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.238.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.239.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.240.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.241.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.242.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.243.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.244.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.245.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.246.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.247.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.248.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.249.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.250.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.251.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.252.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.253.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.254.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.255.down_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.128.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.128.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.129.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.129.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.130.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.130.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.131.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.131.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.132.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.132.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.133.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.133.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.134.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.134.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.135.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.135.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.136.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.136.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.137.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.137.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.138.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.138.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.139.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.139.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.140.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.140.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.141.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.141.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.142.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.142.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.143.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.143.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.144.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.144.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.145.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.145.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.146.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.146.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.147.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.147.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.148.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.148.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.149.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.149.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.150.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.150.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.151.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.151.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.152.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.152.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.153.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.153.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.154.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.154.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.155.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.155.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.156.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.156.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.157.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.157.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.158.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.158.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.159.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.159.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.160.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.160.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.161.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.161.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.162.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.162.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.163.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.163.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.164.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.164.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.165.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.165.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.166.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.166.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.167.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.167.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.168.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.168.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.169.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.169.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.170.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.170.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.171.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.171.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.172.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.172.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.173.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.173.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.174.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.174.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.175.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.175.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.176.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.176.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.177.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.177.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.178.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.178.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.179.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.179.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.180.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.180.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.181.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.181.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.182.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.182.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.183.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.183.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.184.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.184.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.185.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.185.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.186.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.186.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.187.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.187.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.188.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.188.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.189.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.189.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.190.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.190.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.191.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.191.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.192.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.192.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.193.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.193.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.194.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.194.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.195.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.195.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.196.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.196.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.197.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.197.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.198.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.198.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.199.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.199.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.200.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.200.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.201.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.201.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.202.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.202.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.203.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.203.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.204.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.204.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.205.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.205.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.206.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.206.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.207.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.207.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.208.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.208.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.209.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.209.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.210.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.210.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.211.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.211.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.212.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.212.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.213.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.213.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.214.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.214.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.215.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.215.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.216.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.216.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.217.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.217.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.218.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.218.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.219.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.219.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.220.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.220.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.221.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.221.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.222.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.222.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.223.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.223.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.224.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.224.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.225.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.225.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.226.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.226.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.227.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.227.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.228.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.228.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.229.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.229.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.230.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.230.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.231.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.231.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.232.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.232.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.233.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.233.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.234.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.234.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.235.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.235.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.236.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.236.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.237.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.237.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.238.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.238.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.239.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.239.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.240.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.240.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.241.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.241.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.242.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.242.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.243.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.243.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.244.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.244.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.245.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.245.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.246.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.246.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.247.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.247.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.248.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.248.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.249.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.249.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.250.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.250.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.251.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.251.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.252.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.252.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.253.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.253.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.254.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.254.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.255.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.5.mlp.experts.255.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.128.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.128.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.129.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.129.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.130.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.130.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.131.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.131.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.132.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.132.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.133.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.133.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.134.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.134.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.135.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.135.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.136.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.136.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.137.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.137.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.138.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.138.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.139.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.139.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.140.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.140.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.141.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.141.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.142.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.142.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.143.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.143.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.144.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.144.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.145.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.145.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.146.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.146.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.147.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.147.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.148.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.148.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.149.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.149.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.150.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.150.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.151.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.151.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.152.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.152.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.153.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.153.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.154.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.154.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.155.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.155.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.156.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.156.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.157.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.157.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.158.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.158.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.159.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.159.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.160.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.160.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.161.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.161.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.162.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.162.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.163.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.163.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.164.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.164.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.165.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.165.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.166.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.166.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.167.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.167.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.168.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.168.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.169.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.169.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.170.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.170.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.171.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.171.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.172.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.172.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.173.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.173.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.174.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.174.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.175.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.175.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.176.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.176.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.177.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.177.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.178.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.178.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.179.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.179.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.180.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.180.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.181.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.181.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.182.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.182.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.183.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.183.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.184.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.184.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.185.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.185.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.186.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.186.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.187.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.187.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.188.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.188.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.189.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.189.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.190.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.190.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.191.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.191.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.192.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.192.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.193.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.193.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.194.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.194.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.195.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.195.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.196.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.196.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.197.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.197.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.198.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.198.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.199.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.199.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.200.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.200.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.201.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.201.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.202.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.202.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.203.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.203.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.204.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.204.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.205.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.205.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.206.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.206.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.207.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.207.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.208.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.208.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.209.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.209.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.210.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.210.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.211.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.211.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.212.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.212.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.213.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.213.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.214.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.214.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.215.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.215.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.216.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.216.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.217.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.217.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.218.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.218.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.219.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.219.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.220.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.220.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.221.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.221.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.222.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.222.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.223.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.223.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.224.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.224.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.225.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.225.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.226.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.226.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.227.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.227.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.228.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.228.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.229.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.229.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.230.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.230.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.231.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.231.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.232.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.232.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.233.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.233.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.234.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.234.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.235.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.235.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.236.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.236.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.237.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.237.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.238.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.238.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.239.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.239.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.240.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.240.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.241.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.241.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.242.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.242.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.243.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.243.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.244.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.244.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.245.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.245.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.246.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.246.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.247.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.247.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.248.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.248.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.249.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.249.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.250.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.250.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.251.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.251.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.252.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.252.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.253.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.253.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.254.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.254.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.255.gate_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.255.up_proj.weight": "model-00004-of-00022.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.128.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.129.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.130.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.131.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.132.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.133.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.134.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.135.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.136.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.137.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.138.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.139.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.140.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.141.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.142.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.143.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.144.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.145.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.146.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.147.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.148.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.149.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.150.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.151.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.152.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.153.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.154.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.155.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.156.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.157.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.158.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.159.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.160.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.161.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.162.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.163.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.164.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.165.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.166.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.167.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.168.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.169.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.170.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.171.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.172.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.173.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.174.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.175.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.176.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.177.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.178.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.179.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.180.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.181.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.182.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.183.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.184.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.185.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.186.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.187.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.188.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.189.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.190.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.191.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.192.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.193.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.194.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.195.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.196.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.197.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.198.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.199.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.200.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.201.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.202.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.203.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.204.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.205.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.206.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.207.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.208.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.209.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.210.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.211.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.212.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.213.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.214.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.215.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.216.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.217.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.218.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.219.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.220.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.221.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.222.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.223.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.224.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.225.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.226.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.227.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.228.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.229.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.230.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.231.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.232.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.233.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.234.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.235.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.236.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.237.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.238.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.239.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.240.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.241.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.242.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.243.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.244.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.245.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.246.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.247.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.248.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.249.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.250.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.251.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.252.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.253.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.254.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.6.mlp.experts.255.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.128.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.128.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.129.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.129.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.130.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.130.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.131.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.131.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.132.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.132.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.133.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.133.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.134.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.134.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.135.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.135.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.136.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.136.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.137.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.137.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.138.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.138.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.139.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.139.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.140.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.140.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.141.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.141.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.142.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.142.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.143.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.143.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.144.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.144.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.145.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.145.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.146.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.146.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.147.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.147.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.148.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.148.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.149.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.149.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.150.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.150.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.151.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.151.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.152.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.152.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.153.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.153.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.154.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.154.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.155.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.155.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.156.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.156.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.157.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.157.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.158.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.158.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.159.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.159.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.160.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.160.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.161.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.161.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.162.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.162.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.163.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.163.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.164.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.164.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.165.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.165.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.166.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.166.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.167.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.167.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.168.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.168.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.169.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.169.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.170.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.170.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.171.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.171.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.172.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.172.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.173.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.173.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.174.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.174.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.175.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.175.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.176.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.176.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.177.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.177.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.178.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.178.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.179.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.179.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.180.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.180.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.181.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.181.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.182.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.182.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.183.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.183.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.184.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.184.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.185.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.185.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.186.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.186.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.187.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.187.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.188.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.188.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.189.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.189.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.190.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.190.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.191.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.191.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.192.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.192.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.193.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.193.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.194.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.194.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.195.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.195.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.196.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.196.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.197.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.197.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.198.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.198.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.199.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.199.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.200.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.200.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.201.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.201.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.202.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.202.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.203.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.203.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.204.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.204.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.205.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.205.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.206.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.206.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.207.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.207.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.208.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.208.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.209.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.209.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.210.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.210.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.211.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.211.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.212.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.212.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.213.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.213.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.214.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.214.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.215.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.215.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.216.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.216.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.217.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.217.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.218.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.218.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.219.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.219.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.220.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.220.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.221.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.221.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.222.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.222.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.223.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.223.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.224.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.224.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.225.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.225.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.226.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.226.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.227.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.227.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.228.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.228.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.229.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.229.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.230.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.230.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.231.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.231.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.232.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.232.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.233.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.233.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.234.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.234.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.235.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.235.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.236.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.236.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.237.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.237.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.238.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.238.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.239.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.239.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.240.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.240.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.241.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.241.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.242.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.242.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.243.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.243.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.244.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.244.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.245.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.245.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.246.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.246.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.247.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.247.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.248.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.248.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.249.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.249.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.250.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.250.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.251.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.251.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.252.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.252.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.253.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.253.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.254.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.254.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.255.gate_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.255.up_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.128.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.129.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.130.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.131.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.132.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.133.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.134.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.135.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.136.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.137.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.138.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.139.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.140.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.141.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.142.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.143.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.144.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.145.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.146.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.147.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.148.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.149.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.150.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.151.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.152.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.153.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.154.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.155.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.156.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.157.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.158.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.159.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.160.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.161.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.162.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.163.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.164.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.165.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.166.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.167.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.168.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.169.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.170.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.171.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.172.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.173.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.174.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.175.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.176.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.177.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.178.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.179.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.180.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.181.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.182.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.183.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.184.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.185.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.186.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.187.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.188.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.189.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.190.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.191.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.192.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.193.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.194.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.195.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.196.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.197.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.198.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.199.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.200.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.201.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.202.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.203.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.204.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.205.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.206.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.207.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.208.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.209.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.210.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.211.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.212.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.213.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.214.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.215.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.216.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.217.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.218.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.219.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.220.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.221.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.222.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.223.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.224.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.225.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.226.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.227.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.228.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.229.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.230.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.231.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.232.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.233.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.234.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.235.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.236.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.237.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.238.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.239.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.240.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.241.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.242.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.243.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.244.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.245.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.246.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.247.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.248.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.249.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.250.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.251.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.252.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.253.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.254.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.7.mlp.experts.255.down_proj.weight": "model-00005-of-00022.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.128.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.128.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.129.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.129.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.130.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.130.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.131.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.131.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.132.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.132.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.133.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.133.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.134.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.134.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.135.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.135.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.136.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.136.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.137.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.137.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.138.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.138.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.139.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.139.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.140.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.140.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.141.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.141.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.142.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.142.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.143.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.143.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.144.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.144.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.145.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.145.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.146.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.146.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.147.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.147.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.148.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.148.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.149.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.149.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.150.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.150.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.151.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.151.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.152.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.152.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.153.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.153.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.154.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.154.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.155.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.155.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.156.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.156.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.157.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.157.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.158.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.158.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.159.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.159.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.160.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.160.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.161.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.161.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.162.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.162.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.163.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.163.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.164.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.164.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.165.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.165.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.166.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.166.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.167.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.167.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.168.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.168.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.169.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.169.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.170.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.170.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.171.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.171.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.172.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.172.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.173.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.173.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.174.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.174.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.175.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.175.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.176.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.176.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.177.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.177.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.178.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.178.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.179.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.179.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.180.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.180.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.181.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.181.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.182.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.182.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.183.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.183.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.184.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.184.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.185.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.185.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.186.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.186.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.187.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.187.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.188.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.188.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.189.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.189.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.190.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.190.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.191.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.191.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.192.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.192.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.193.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.193.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.194.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.194.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.195.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.195.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.196.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.196.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.197.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.197.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.198.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.198.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.199.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.199.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.200.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.200.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.201.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.201.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.202.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.202.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.203.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.203.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.204.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.204.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.205.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.205.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.206.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.206.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.207.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.207.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.208.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.208.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.209.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.209.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.210.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.210.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.211.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.211.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.212.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.212.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.213.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.213.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.214.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.214.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.215.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.215.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.216.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.216.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.217.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.217.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.218.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.218.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.219.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.219.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.220.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.220.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.221.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.221.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.222.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.222.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.223.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.223.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.224.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.224.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.225.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.225.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.226.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.226.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.227.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.227.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.228.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.228.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.229.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.229.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.230.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.230.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.231.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.231.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.232.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.232.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.233.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.233.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.234.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.234.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.235.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.235.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.236.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.236.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.237.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.237.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.238.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.238.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.239.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.239.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.240.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.240.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.241.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.241.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.242.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.242.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.243.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.243.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.244.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.244.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.245.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.245.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.246.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.246.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.247.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.247.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.248.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.248.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.249.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.249.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.250.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.250.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.251.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.251.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.252.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.252.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.253.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.253.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.254.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.254.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.255.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.255.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.128.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.128.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.129.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.129.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.130.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.130.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.131.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.131.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.132.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.132.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.133.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.133.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.134.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.134.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.135.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.135.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.136.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.136.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.137.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.137.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.138.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.138.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.139.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.139.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.140.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.140.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.141.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.141.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.142.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.142.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.143.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.143.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.144.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.144.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.145.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.145.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.146.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.146.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.147.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.147.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.148.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.148.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.149.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.149.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.150.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.150.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.151.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.151.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.152.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.152.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.153.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.153.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.154.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.154.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.155.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.155.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.156.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.156.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.157.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.157.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.158.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.158.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.159.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.159.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.160.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.160.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.161.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.161.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.162.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.162.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.163.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.163.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.164.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.164.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.165.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.165.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.166.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.166.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.167.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.167.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.168.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.168.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.169.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.169.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.170.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.170.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.171.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.171.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.172.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.172.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.173.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.173.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.174.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.174.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.175.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.175.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.176.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.176.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.177.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.177.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.178.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.178.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.179.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.179.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.180.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.180.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.181.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.181.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.182.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.182.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.183.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.183.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.184.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.184.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.185.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.185.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.186.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.186.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.187.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.187.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.188.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.188.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.189.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.189.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.190.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.190.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.191.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.191.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.192.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.192.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.193.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.193.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.194.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.194.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.195.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.195.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.196.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.196.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.197.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.197.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.198.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.198.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.199.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.199.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.200.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.200.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.201.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.201.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.202.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.202.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.203.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.203.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.204.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.204.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.205.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.205.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.206.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.206.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.207.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.207.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.208.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.208.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.209.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.209.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.210.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.210.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.211.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.211.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.212.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.212.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.213.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.213.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.214.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.214.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.215.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.215.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.216.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.216.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.217.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.217.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.218.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.218.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.219.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.219.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.220.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.220.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.221.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.221.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.222.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.222.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.223.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.223.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.224.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.224.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.225.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.225.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.226.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.226.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.227.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.227.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.228.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.228.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.229.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.229.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.230.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.230.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.231.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.231.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.232.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.232.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.233.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.233.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.234.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.234.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.235.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.235.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.236.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.236.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.237.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.237.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.238.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.238.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.239.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.239.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.240.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.240.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.241.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.241.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.242.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.242.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.243.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.243.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.244.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.244.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.245.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.245.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.246.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.246.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.247.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.247.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.248.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.248.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.249.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.249.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.250.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.250.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.251.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.251.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.252.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.252.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.253.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.253.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.254.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.254.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.255.gate_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.255.up_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.128.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.129.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.130.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.131.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.132.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.133.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.134.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.135.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.136.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.137.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.138.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.139.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.140.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.141.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.142.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.143.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.144.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.145.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.146.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.147.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.148.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.149.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.150.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.151.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.152.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.153.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.154.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.155.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.156.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.157.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.158.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.159.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.160.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.161.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.162.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.163.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.164.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.165.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.166.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.167.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.168.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.169.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.170.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.171.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.172.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.173.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.174.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.175.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.176.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.177.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.178.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.179.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.180.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.181.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.182.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.183.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.184.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.185.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.186.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.187.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.188.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.189.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.190.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.191.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.192.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.193.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.194.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.195.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.196.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.197.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.198.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.199.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.200.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.201.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.202.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.203.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.204.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.205.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.206.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.207.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.208.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.209.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.210.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.211.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.212.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.213.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.214.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.215.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.216.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.217.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.218.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.219.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.220.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.221.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.222.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.223.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.224.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.225.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.226.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.227.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.228.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.229.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.230.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.231.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.232.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.233.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.234.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.235.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.236.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.237.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.238.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.239.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.240.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.241.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.242.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.243.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.244.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.245.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.246.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.247.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.248.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.249.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.250.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.251.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.252.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.253.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.254.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.8.mlp.experts.255.down_proj.weight": "model-00006-of-00022.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.128.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.129.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.130.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.131.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.132.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.133.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.134.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.135.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.136.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.137.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.138.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.139.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.140.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.141.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.142.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.143.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.144.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.145.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.146.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.147.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.148.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.149.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.150.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.151.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.152.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.153.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.154.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.155.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.156.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.157.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.158.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.159.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.160.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.161.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.162.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.163.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.164.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.165.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.166.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.167.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.168.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.169.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.170.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.171.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.172.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.173.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.174.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.175.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.176.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.177.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.178.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.179.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.180.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.181.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.182.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.183.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.184.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.185.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.186.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.187.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.188.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.189.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.190.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.191.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.192.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.193.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.194.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.195.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.196.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.197.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.198.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.199.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.200.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.201.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.202.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.203.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.204.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.205.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.206.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.207.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.208.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.209.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.210.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.211.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.212.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.213.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.214.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.215.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.216.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.217.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.218.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.219.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.220.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.221.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.222.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.223.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.224.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.225.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.226.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.227.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.228.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.229.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.230.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.231.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.232.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.233.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.234.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.235.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.236.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.237.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.238.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.239.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.240.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.241.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.242.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.243.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.244.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.245.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.246.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.247.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.248.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.249.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.250.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.251.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.252.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.253.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.254.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.9.mlp.experts.255.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.128.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.128.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.129.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.129.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.130.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.130.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.131.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.131.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.132.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.132.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.133.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.133.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.134.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.134.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.135.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.135.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.136.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.136.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.137.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.137.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.138.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.138.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.139.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.139.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.140.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.140.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.141.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.141.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.142.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.142.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.143.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.143.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.144.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.144.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.145.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.145.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.146.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.146.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.147.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.147.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.148.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.148.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.149.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.149.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.150.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.150.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.151.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.151.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.152.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.152.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.153.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.153.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.154.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.154.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.155.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.155.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.156.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.156.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.157.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.157.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.158.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.158.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.159.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.159.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.160.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.160.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.161.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.161.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.162.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.162.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.163.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.163.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.164.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.164.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.165.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.165.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.166.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.166.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.167.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.167.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.168.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.168.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.169.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.169.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.170.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.170.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.171.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.171.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.172.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.172.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.173.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.173.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.174.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.174.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.175.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.175.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.176.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.176.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.177.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.177.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.178.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.178.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.179.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.179.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.180.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.180.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.181.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.181.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.182.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.182.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.183.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.183.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.184.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.184.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.185.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.185.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.186.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.186.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.187.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.187.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.188.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.188.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.189.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.189.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.190.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.190.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.191.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.191.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.192.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.192.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.193.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.193.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.194.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.194.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.195.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.195.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.196.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.196.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.197.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.197.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.198.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.198.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.199.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.199.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.200.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.200.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.201.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.201.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.202.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.202.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.203.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.203.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.204.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.204.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.205.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.205.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.206.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.206.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.207.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.207.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.208.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.208.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.209.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.209.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.210.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.210.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.211.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.211.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.212.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.212.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.213.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.213.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.214.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.214.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.215.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.215.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.216.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.216.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.217.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.217.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.218.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.218.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.219.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.219.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.220.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.220.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.221.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.221.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.222.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.222.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.223.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.223.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.224.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.224.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.225.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.225.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.226.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.226.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.227.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.227.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.228.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.228.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.229.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.229.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.230.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.230.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.231.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.231.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.232.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.232.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.233.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.233.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.234.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.234.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.235.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.235.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.236.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.236.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.237.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.237.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.238.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.238.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.239.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.239.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.240.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.240.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.241.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.241.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.242.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.242.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.243.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.243.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.244.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.244.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.245.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.245.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.246.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.246.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.247.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.247.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.248.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.248.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.249.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.249.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.250.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.250.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.251.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.251.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.252.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.252.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.253.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.253.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.254.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.254.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.255.gate_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.255.up_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.128.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.129.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.130.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.131.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.132.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.133.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.134.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.135.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.136.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.137.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.138.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.139.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.140.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.141.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.142.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.143.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.144.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.145.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.146.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.147.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.148.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.149.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.150.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.151.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.152.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.153.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.154.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.155.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.156.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.157.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.158.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.159.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.160.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.161.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.162.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.163.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.164.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.165.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.166.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.167.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.168.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.169.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.170.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.171.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.172.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.173.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.174.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.175.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.176.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.177.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.178.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.179.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.180.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.181.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.182.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.183.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.184.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.185.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.186.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.187.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.188.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.189.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.190.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.191.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.192.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.193.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.194.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.195.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.196.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.197.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.198.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.199.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.200.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.201.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.202.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.203.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.204.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.205.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.206.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.207.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.208.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.209.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.210.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.211.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.212.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.213.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.214.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.215.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.216.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.217.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.218.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.219.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.220.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.221.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.222.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.223.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.224.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.225.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.226.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.227.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.228.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.229.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.230.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.231.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.232.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.233.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.234.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.235.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.236.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.237.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.238.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.239.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.240.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.241.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.242.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.243.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.244.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.245.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.246.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.247.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.248.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.249.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.250.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.251.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.252.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.253.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.254.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.10.mlp.experts.255.down_proj.weight": "model-00007-of-00022.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.128.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.128.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.129.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.129.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.130.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.130.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.131.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.131.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.132.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.132.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.133.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.133.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.134.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.134.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.135.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.135.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.136.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.136.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.137.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.137.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.138.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.138.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.139.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.139.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.140.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.140.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.141.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.141.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.142.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.142.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.143.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.143.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.144.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.144.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.145.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.145.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.146.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.146.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.147.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.147.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.148.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.148.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.149.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.149.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.150.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.150.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.151.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.151.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.152.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.152.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.153.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.153.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.154.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.154.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.155.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.155.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.156.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.156.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.157.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.157.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.158.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.158.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.159.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.159.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.160.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.160.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.161.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.161.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.162.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.162.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.163.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.163.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.164.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.164.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.165.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.165.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.166.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.166.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.167.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.167.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.168.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.168.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.169.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.169.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.170.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.170.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.171.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.171.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.172.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.172.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.173.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.173.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.174.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.174.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.175.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.175.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.176.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.176.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.177.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.177.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.178.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.178.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.179.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.179.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.180.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.180.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.181.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.181.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.182.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.182.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.183.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.183.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.184.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.184.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.185.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.185.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.186.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.186.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.187.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.187.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.188.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.188.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.189.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.189.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.190.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.190.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.191.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.191.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.192.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.192.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.193.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.193.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.194.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.194.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.195.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.195.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.196.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.196.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.197.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.197.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.198.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.198.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.199.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.199.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.200.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.200.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.201.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.201.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.202.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.202.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.203.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.203.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.204.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.204.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.205.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.205.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.206.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.206.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.207.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.207.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.208.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.208.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.209.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.209.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.210.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.210.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.211.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.211.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.212.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.212.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.213.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.213.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.214.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.214.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.215.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.215.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.216.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.216.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.217.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.217.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.218.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.218.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.219.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.219.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.220.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.220.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.221.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.221.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.222.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.222.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.223.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.223.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.224.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.224.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.225.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.225.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.226.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.226.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.227.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.227.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.228.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.228.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.229.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.229.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.230.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.230.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.231.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.231.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.232.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.232.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.233.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.233.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.234.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.234.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.235.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.235.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.236.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.236.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.237.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.237.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.238.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.238.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.239.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.239.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.240.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.240.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.241.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.241.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.242.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.242.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.243.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.243.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.244.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.244.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.245.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.245.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.246.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.246.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.247.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.247.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.248.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.248.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.249.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.249.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.250.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.250.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.251.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.251.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.252.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.252.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.253.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.253.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.254.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.254.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.255.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.12.mlp.experts.255.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.128.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.129.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.130.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.131.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.132.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.133.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.134.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.135.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.136.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.137.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.138.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.139.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.140.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.141.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.142.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.143.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.144.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.145.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.146.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.147.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.148.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.149.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.150.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.151.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.152.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.153.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.154.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.155.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.156.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.157.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.158.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.159.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.160.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.161.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.162.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.163.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.164.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.165.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.166.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.167.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.168.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.169.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.170.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.171.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.172.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.173.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.174.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.175.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.176.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.177.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.178.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.179.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.180.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.181.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.182.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.183.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.184.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.185.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.186.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.187.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.188.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.189.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.190.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.191.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.192.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.193.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.194.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.195.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.196.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.197.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.198.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.199.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.200.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.201.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.202.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.203.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.204.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.205.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.206.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.207.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.208.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.209.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.210.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.211.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.212.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.213.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.214.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.215.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.216.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.217.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.218.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.219.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.220.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.221.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.222.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.223.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.224.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.225.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.226.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.227.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.228.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.229.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.230.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.231.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.232.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.233.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.234.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.235.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.236.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.237.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.238.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.239.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.240.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.241.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.242.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.243.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.244.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.245.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.246.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.247.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.248.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.249.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.250.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.251.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.252.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.253.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.254.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.255.down_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.128.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.128.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.129.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.129.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.130.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.130.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.131.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.131.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.132.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.132.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.133.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.133.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.134.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.134.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.135.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.135.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.136.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.136.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.137.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.137.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.138.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.138.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.139.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.139.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.140.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.140.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.141.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.141.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.142.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.142.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.143.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.143.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.144.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.144.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.145.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.145.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.146.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.146.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.147.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.147.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.148.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.148.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.149.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.149.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.150.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.150.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.151.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.151.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.152.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.152.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.153.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.153.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.154.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.154.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.155.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.155.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.156.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.156.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.157.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.157.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.158.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.158.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.159.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.159.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.160.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.160.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.161.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.161.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.162.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.162.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.163.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.163.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.164.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.164.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.165.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.165.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.166.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.166.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.167.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.167.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.168.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.168.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.169.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.169.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.170.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.170.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.171.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.171.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.172.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.172.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.173.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.173.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.174.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.174.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.175.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.175.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.176.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.176.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.177.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.177.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.178.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.178.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.179.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.179.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.180.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.180.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.181.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.181.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.182.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.182.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.183.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.183.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.184.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.184.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.185.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.185.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.186.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.186.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.187.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.187.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.188.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.188.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.189.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.189.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.190.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.190.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.191.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.191.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.192.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.192.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.193.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.193.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.194.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.194.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.195.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.195.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.196.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.196.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.197.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.197.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.198.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.198.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.199.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.199.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.200.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.200.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.201.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.201.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.202.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.202.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.203.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.203.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.204.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.204.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.205.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.205.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.206.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.206.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.207.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.207.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.208.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.208.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.209.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.209.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.210.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.210.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.211.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.211.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.212.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.212.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.213.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.213.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.214.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.214.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.215.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.215.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.216.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.216.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.217.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.217.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.218.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.218.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.219.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.219.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.220.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.220.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.221.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.221.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.222.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.222.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.223.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.223.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.224.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.224.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.225.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.225.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.226.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.226.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.227.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.227.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.228.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.228.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.229.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.229.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.230.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.230.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.231.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.231.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.232.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.232.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.233.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.233.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.234.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.234.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.235.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.235.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.236.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.236.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.237.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.237.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.238.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.238.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.239.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.239.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.240.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.240.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.241.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.241.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.242.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.242.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.243.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.243.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.244.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.244.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.245.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.245.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.246.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.246.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.247.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.247.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.248.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.248.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.249.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.249.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.250.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.250.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.251.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.251.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.252.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.252.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.253.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.253.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.254.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.254.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.255.gate_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.11.mlp.experts.255.up_proj.weight": "model-00008-of-00022.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.128.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.129.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.130.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.131.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.132.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.133.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.134.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.135.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.136.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.137.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.138.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.139.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.140.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.141.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.142.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.143.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.144.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.145.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.146.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.147.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.148.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.149.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.150.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.151.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.152.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.153.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.154.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.155.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.156.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.157.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.158.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.159.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.160.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.161.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.162.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.163.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.164.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.165.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.166.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.167.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.168.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.169.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.170.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.171.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.172.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.173.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.174.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.175.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.176.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.177.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.178.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.179.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.180.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.181.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.182.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.183.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.184.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.185.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.186.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.187.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.188.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.189.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.190.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.191.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.192.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.193.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.194.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.195.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.196.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.197.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.198.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.199.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.200.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.201.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.202.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.203.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.204.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.205.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.206.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.207.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.208.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.209.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.210.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.211.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.212.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.213.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.214.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.215.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.216.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.217.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.218.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.219.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.220.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.221.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.222.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.223.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.224.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.225.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.226.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.227.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.228.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.229.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.230.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.231.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.232.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.233.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.234.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.235.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.236.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.237.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.238.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.239.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.240.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.241.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.242.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.243.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.244.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.245.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.246.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.247.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.248.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.249.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.250.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.251.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.252.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.253.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.254.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.255.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.128.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.128.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.129.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.129.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.130.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.130.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.131.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.131.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.132.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.132.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.133.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.133.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.134.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.134.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.135.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.135.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.136.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.136.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.137.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.137.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.138.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.138.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.139.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.139.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.140.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.140.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.141.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.141.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.142.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.142.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.143.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.143.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.144.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.144.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.145.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.145.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.146.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.146.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.147.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.147.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.148.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.148.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.149.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.149.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.150.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.150.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.151.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.151.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.152.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.152.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.153.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.153.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.154.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.154.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.155.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.155.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.156.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.156.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.157.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.157.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.158.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.158.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.159.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.159.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.160.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.160.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.161.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.161.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.162.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.162.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.163.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.163.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.164.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.164.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.165.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.165.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.166.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.166.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.167.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.167.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.168.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.168.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.169.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.169.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.170.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.170.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.171.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.171.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.172.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.172.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.173.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.173.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.174.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.174.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.175.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.175.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.176.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.176.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.177.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.177.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.178.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.178.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.179.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.179.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.180.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.180.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.181.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.181.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.182.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.182.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.183.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.183.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.184.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.184.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.185.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.185.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.186.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.186.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.187.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.187.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.188.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.188.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.189.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.189.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.190.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.190.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.191.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.191.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.192.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.192.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.193.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.193.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.194.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.194.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.195.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.195.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.196.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.196.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.197.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.197.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.198.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.198.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.199.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.199.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.200.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.200.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.201.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.201.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.202.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.202.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.203.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.203.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.204.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.204.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.205.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.205.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.206.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.206.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.207.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.207.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.208.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.208.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.209.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.209.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.210.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.210.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.211.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.211.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.212.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.212.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.213.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.213.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.214.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.214.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.215.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.215.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.216.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.216.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.217.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.217.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.218.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.218.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.219.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.219.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.220.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.220.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.221.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.221.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.222.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.222.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.223.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.223.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.224.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.224.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.225.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.225.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.226.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.226.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.227.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.227.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.228.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.228.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.229.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.229.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.230.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.230.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.231.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.231.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.232.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.232.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.233.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.233.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.234.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.234.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.235.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.235.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.236.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.236.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.237.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.237.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.238.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.238.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.239.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.239.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.240.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.240.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.241.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.241.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.242.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.242.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.243.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.243.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.244.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.244.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.245.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.245.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.246.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.246.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.247.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.247.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.248.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.248.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.249.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.249.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.250.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.250.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.251.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.251.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.252.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.252.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.253.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.253.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.254.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.254.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.255.gate_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.13.mlp.experts.255.up_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.128.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.129.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.130.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.131.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.132.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.133.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.134.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.135.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.136.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.137.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.138.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.139.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.140.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.141.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.142.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.143.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.144.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.145.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.146.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.147.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.148.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.149.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.150.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.151.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.152.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.153.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.154.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.155.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.156.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.157.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.158.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.159.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.160.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.161.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.162.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.163.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.164.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.165.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.166.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.167.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.168.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.169.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.170.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.171.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.172.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.173.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.174.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.175.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.176.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.177.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.178.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.179.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.180.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.181.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.182.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.183.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.184.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.185.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.186.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.187.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.188.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.189.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.190.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.191.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.192.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.193.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.194.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.195.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.196.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.197.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.198.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.199.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.200.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.201.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.202.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.203.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.204.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.205.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.206.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.207.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.208.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.209.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.210.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.211.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.212.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.213.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.214.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.215.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.216.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.217.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.218.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.219.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.220.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.221.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.222.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.223.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.224.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.225.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.226.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.227.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.228.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.229.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.230.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.231.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.232.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.233.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.234.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.235.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.236.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.237.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.238.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.239.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.240.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.241.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.242.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.243.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.244.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.245.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.246.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.247.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.248.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.249.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.250.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.251.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.252.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.253.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.254.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.12.mlp.experts.255.down_proj.weight": "model-00009-of-00022.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.128.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.128.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.129.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.129.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.130.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.130.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.131.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.131.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.132.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.132.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.133.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.133.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.134.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.134.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.135.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.135.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.136.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.136.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.137.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.137.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.138.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.138.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.139.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.139.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.140.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.140.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.141.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.141.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.142.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.142.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.143.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.143.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.144.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.144.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.145.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.145.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.146.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.146.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.147.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.147.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.148.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.148.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.149.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.149.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.150.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.150.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.151.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.151.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.152.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.152.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.153.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.153.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.154.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.154.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.155.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.155.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.156.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.156.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.157.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.157.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.158.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.158.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.159.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.159.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.160.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.160.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.161.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.161.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.162.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.162.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.163.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.163.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.164.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.164.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.165.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.165.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.166.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.166.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.167.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.167.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.168.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.168.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.169.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.169.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.170.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.170.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.171.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.171.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.172.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.172.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.173.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.173.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.174.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.174.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.175.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.175.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.176.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.176.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.177.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.177.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.178.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.178.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.179.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.179.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.180.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.180.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.181.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.181.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.182.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.182.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.183.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.183.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.184.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.184.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.185.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.185.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.186.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.186.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.187.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.187.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.188.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.188.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.189.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.189.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.190.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.190.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.191.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.191.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.192.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.192.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.193.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.193.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.194.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.194.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.195.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.195.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.196.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.196.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.197.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.197.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.198.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.198.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.199.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.199.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.200.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.200.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.201.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.201.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.202.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.202.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.203.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.203.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.204.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.204.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.205.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.205.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.206.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.206.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.207.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.207.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.208.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.208.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.209.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.209.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.210.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.210.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.211.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.211.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.212.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.212.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.213.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.213.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.214.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.214.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.215.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.215.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.216.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.216.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.217.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.217.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.218.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.218.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.219.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.219.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.220.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.220.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.221.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.221.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.222.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.222.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.223.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.223.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.224.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.224.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.225.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.225.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.226.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.226.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.227.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.227.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.228.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.228.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.229.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.229.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.230.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.230.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.231.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.231.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.232.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.232.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.233.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.233.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.234.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.234.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.235.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.235.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.236.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.236.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.237.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.237.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.238.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.238.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.239.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.239.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.240.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.240.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.241.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.241.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.242.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.242.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.243.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.243.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.244.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.244.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.245.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.245.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.246.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.246.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.247.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.247.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.248.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.248.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.249.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.249.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.250.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.250.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.251.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.251.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.252.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.252.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.253.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.253.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.254.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.254.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.255.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.255.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.128.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.129.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.130.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.131.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.132.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.133.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.134.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.135.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.136.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.137.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.138.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.139.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.140.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.141.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.142.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.143.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.144.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.145.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.146.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.147.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.148.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.149.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.150.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.151.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.152.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.153.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.154.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.155.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.156.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.157.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.158.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.159.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.160.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.161.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.162.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.163.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.164.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.165.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.166.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.167.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.168.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.169.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.170.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.171.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.172.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.173.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.174.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.175.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.176.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.177.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.178.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.179.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.180.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.181.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.182.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.183.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.184.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.185.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.186.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.187.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.188.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.189.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.190.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.191.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.192.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.193.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.194.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.195.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.196.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.197.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.198.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.199.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.200.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.201.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.202.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.203.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.204.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.205.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.206.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.207.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.208.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.209.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.210.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.211.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.212.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.213.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.214.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.215.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.216.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.217.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.218.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.219.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.220.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.221.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.222.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.223.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.224.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.225.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.226.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.227.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.228.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.229.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.230.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.231.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.232.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.233.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.234.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.235.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.236.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.237.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.238.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.239.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.240.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.241.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.242.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.243.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.244.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.245.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.246.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.247.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.248.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.249.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.250.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.251.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.252.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.253.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.254.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.14.mlp.experts.255.down_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.128.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.128.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.129.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.129.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.130.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.130.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.131.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.131.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.132.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.132.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.133.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.133.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.134.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.134.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.135.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.135.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.136.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.136.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.137.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.137.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.138.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.138.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.139.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.139.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.140.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.140.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.141.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.141.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.142.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.142.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.143.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.143.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.144.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.144.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.145.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.145.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.146.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.146.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.147.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.147.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.148.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.148.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.149.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.149.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.150.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.150.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.151.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.151.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.152.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.152.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.153.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.153.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.154.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.154.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.155.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.155.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.156.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.156.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.157.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.157.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.158.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.158.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.159.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.159.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.160.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.160.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.161.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.161.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.162.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.162.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.163.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.163.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.164.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.164.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.165.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.165.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.166.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.166.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.167.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.167.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.168.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.168.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.169.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.169.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.170.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.170.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.171.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.171.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.172.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.172.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.173.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.173.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.174.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.174.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.175.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.175.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.176.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.176.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.177.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.177.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.178.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.178.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.179.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.179.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.180.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.180.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.181.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.181.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.182.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.182.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.183.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.183.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.184.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.184.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.185.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.185.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.186.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.186.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.187.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.187.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.188.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.188.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.189.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.189.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.190.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.190.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.191.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.191.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.192.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.192.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.193.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.193.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.194.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.194.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.195.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.195.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.196.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.196.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.197.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.197.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.198.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.198.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.199.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.199.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.200.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.200.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.201.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.201.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.202.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.202.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.203.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.203.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.204.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.204.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.205.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.205.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.206.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.206.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.207.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.207.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.208.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.208.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.209.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.209.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.210.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.210.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.211.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.211.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.212.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.212.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.213.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.213.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.214.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.214.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.215.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.215.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.216.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.216.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.217.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.217.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.218.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.218.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.219.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.219.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.220.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.220.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.221.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.221.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.222.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.222.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.223.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.223.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.224.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.224.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.225.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.225.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.226.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.226.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.227.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.227.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.228.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.228.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.229.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.229.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.230.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.230.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.231.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.231.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.232.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.232.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.233.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.233.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.234.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.234.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.235.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.235.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.236.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.236.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.237.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.237.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.238.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.238.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.239.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.239.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.240.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.240.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.241.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.241.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.242.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.242.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.243.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.243.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.244.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.244.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.245.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.245.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.246.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.246.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.247.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.247.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.248.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.248.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.249.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.249.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.250.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.250.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.251.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.251.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.252.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.252.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.253.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.253.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.254.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.254.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.255.gate_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.15.mlp.experts.255.up_proj.weight": "model-00010-of-00022.safetensors", + "model.layers.4.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.6.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.12.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.4.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.14.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.2.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.0.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.13.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.7.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.8.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.14.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.3.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.6.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.5.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.0.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.128.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.128.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.129.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.129.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.130.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.130.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.131.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.131.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.132.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.132.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.133.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.133.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.134.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.134.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.135.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.135.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.136.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.136.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.137.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.137.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.138.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.138.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.139.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.139.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.140.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.140.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.141.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.141.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.142.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.142.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.143.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.143.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.144.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.144.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.145.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.145.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.146.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.146.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.147.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.147.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.148.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.148.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.149.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.149.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.150.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.150.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.151.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.151.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.152.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.152.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.153.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.153.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.154.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.154.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.155.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.155.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.156.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.156.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.157.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.157.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.158.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.158.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.159.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.159.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.160.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.160.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.161.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.161.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.162.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.162.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.163.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.163.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.164.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.164.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.165.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.165.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.166.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.166.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.167.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.167.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.168.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.168.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.169.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.169.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.170.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.170.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.171.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.171.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.172.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.172.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.173.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.173.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.174.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.174.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.175.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.175.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.176.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.176.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.177.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.177.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.178.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.178.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.179.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.179.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.180.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.180.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.181.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.181.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.182.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.182.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.183.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.183.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.184.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.184.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.185.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.185.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.186.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.186.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.187.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.187.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.188.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.188.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.189.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.189.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.190.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.190.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.191.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.191.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.192.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.192.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.193.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.193.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.194.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.194.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.195.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.195.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.196.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.196.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.197.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.197.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.198.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.198.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.199.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.199.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.200.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.200.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.201.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.201.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.202.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.202.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.203.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.203.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.204.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.204.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.205.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.205.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.206.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.206.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.207.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.207.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.208.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.208.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.209.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.209.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.210.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.210.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.211.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.211.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.212.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.212.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.213.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.213.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.214.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.214.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.215.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.215.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.216.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.216.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.217.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.217.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.218.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.218.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.219.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.219.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.220.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.220.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.221.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.221.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.222.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.222.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.223.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.223.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.224.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.224.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.225.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.225.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.226.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.226.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.227.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.227.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.228.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.228.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.229.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.229.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.230.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.230.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.231.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.231.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.232.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.232.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.233.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.233.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.234.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.234.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.235.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.235.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.236.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.236.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.237.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.237.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.238.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.238.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.239.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.239.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.240.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.240.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.241.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.241.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.242.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.242.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.243.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.243.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.244.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.244.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.245.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.245.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.246.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.246.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.247.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.247.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.248.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.248.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.249.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.249.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.250.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.250.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.251.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.251.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.252.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.252.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.253.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.253.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.254.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.254.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.255.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.255.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.10.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.3.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.5.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.1.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.1.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.12.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.11.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.15.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.8.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.7.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.12.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.11.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.2.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.12.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.1.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.13.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.14.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.15.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.4.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.4.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.5.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.11.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.3.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.6.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.8.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.3.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.13.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.0.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.12.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.1.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.3.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.6.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.13.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.4.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.2.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.128.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.129.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.130.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.131.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.132.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.133.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.134.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.135.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.136.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.137.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.138.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.139.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.140.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.141.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.142.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.143.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.144.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.145.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.146.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.147.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.148.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.149.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.150.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.151.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.152.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.153.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.154.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.155.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.156.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.157.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.158.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.159.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.160.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.161.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.162.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.163.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.164.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.165.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.166.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.167.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.168.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.169.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.170.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.171.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.172.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.173.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.174.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.175.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.176.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.177.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.178.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.179.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.180.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.181.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.182.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.183.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.184.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.185.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.186.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.187.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.188.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.189.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.190.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.191.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.192.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.193.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.194.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.195.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.196.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.197.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.198.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.199.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.200.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.201.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.202.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.203.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.204.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.205.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.206.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.207.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.208.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.209.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.210.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.211.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.212.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.213.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.214.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.215.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.216.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.217.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.218.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.219.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.220.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.221.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.222.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.223.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.224.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.225.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.226.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.227.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.228.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.229.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.230.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.231.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.232.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.233.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.234.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.235.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.236.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.237.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.238.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.239.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.240.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.241.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.242.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.243.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.244.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.245.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.246.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.247.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.248.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.249.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.250.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.251.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.252.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.253.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.254.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.16.mlp.experts.255.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.12.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.6.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.9.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.9.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.7.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.0.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.3.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.9.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.12.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.13.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.9.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.2.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.15.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.11.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.11.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.10.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.10.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.14.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.14.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.10.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.4.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.5.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.9.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.5.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.10.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.1.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.9.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.7.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.6.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.9.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.1.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.7.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.8.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.13.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.7.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.10.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.8.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.7.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.10.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.2.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.15.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.gate.expert_bias": "model-00011-of-00022.safetensors", + "model.layers.11.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.11.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.2.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.0.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.4.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.8.attention.key_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.2.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.1.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.3.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.14.input_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.8.mlp.gate.weight": "model-00011-of-00022.safetensors", + "model.layers.5.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.13.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.14.attention.query_key_value.weight": "model-00011-of-00022.safetensors", + "model.layers.6.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.128.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.129.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.130.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.131.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.132.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.133.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.134.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.135.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.136.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.137.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.138.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.139.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.140.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.141.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.142.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.143.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.144.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.145.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.146.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.147.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.148.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.149.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.150.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.151.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.152.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.153.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.154.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.155.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.156.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.157.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.158.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.159.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.160.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.161.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.162.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.163.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.164.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.165.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.166.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.167.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.168.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.169.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.170.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.171.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.172.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.173.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.174.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.175.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.176.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.177.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.178.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.179.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.180.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.181.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.182.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.183.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.184.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.185.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.186.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.187.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.188.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.189.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.190.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.191.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.192.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.193.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.194.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.195.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.196.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.197.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.198.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.199.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.200.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.201.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.202.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.203.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.204.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.205.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.206.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.207.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.208.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.209.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.210.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.211.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.212.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.213.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.214.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.215.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.216.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.217.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.218.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.219.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.220.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.221.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.222.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.223.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.224.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.225.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.226.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.227.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.228.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.229.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.230.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.231.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.232.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.233.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.234.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.235.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.236.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.237.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.238.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.239.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.240.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.241.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.242.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.243.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.244.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.245.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.246.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.247.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.248.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.249.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.250.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.251.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.252.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.253.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.254.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.mlp.experts.255.down_proj.weight": "model-00011-of-00022.safetensors", + "model.layers.15.attention.query_layernorm.weight": "model-00011-of-00022.safetensors", + "model.layers.5.attention.dense.weight": "model-00011-of-00022.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.128.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.129.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.130.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.131.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.132.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.133.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.134.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.135.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.136.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.137.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.138.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.139.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.140.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.141.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.142.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.143.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.144.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.145.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.146.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.147.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.148.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.149.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.150.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.151.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.152.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.153.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.154.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.155.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.156.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.157.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.158.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.159.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.160.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.161.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.162.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.163.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.164.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.165.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.166.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.167.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.168.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.169.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.170.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.171.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.172.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.173.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.174.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.175.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.176.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.177.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.178.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.179.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.180.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.181.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.182.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.183.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.184.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.185.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.186.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.187.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.188.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.189.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.190.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.191.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.192.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.193.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.194.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.195.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.196.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.197.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.198.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.199.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.200.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.201.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.202.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.203.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.204.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.205.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.206.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.207.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.208.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.209.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.210.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.211.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.212.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.213.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.214.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.215.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.216.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.217.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.218.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.219.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.220.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.221.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.222.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.223.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.224.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.225.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.226.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.227.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.228.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.229.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.230.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.231.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.232.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.233.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.234.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.235.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.236.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.237.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.238.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.239.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.240.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.241.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.242.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.243.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.244.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.245.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.246.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.247.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.248.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.249.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.250.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.251.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.252.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.253.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.254.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.255.down_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.128.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.128.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.129.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.129.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.130.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.130.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.131.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.131.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.132.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.132.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.133.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.133.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.134.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.134.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.135.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.135.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.136.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.136.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.137.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.137.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.138.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.138.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.139.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.139.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.140.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.140.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.141.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.141.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.142.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.142.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.143.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.143.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.144.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.144.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.145.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.145.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.146.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.146.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.147.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.147.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.148.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.148.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.149.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.149.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.150.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.150.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.151.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.151.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.152.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.152.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.153.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.153.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.154.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.154.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.155.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.155.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.156.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.156.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.157.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.157.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.158.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.158.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.159.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.159.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.160.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.160.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.161.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.161.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.162.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.162.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.163.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.163.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.164.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.164.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.165.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.165.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.166.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.166.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.167.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.167.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.168.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.168.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.169.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.169.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.170.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.170.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.171.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.171.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.172.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.172.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.173.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.173.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.174.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.174.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.175.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.175.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.176.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.176.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.177.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.177.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.178.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.178.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.179.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.179.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.180.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.180.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.181.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.181.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.182.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.182.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.183.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.183.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.184.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.184.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.185.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.185.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.186.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.186.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.187.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.187.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.188.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.188.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.189.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.189.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.190.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.190.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.191.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.191.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.192.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.192.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.193.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.193.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.194.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.194.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.195.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.195.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.196.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.196.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.197.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.197.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.198.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.198.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.199.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.199.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.200.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.200.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.201.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.201.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.202.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.202.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.203.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.203.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.204.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.204.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.205.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.205.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.206.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.206.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.207.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.207.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.208.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.208.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.209.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.209.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.210.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.210.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.211.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.211.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.212.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.212.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.213.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.213.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.214.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.214.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.215.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.215.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.216.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.216.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.217.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.217.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.218.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.218.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.219.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.219.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.220.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.220.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.221.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.221.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.222.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.222.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.223.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.223.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.224.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.224.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.225.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.225.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.226.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.226.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.227.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.227.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.228.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.228.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.229.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.229.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.230.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.230.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.231.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.231.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.232.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.232.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.233.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.233.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.234.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.234.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.235.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.235.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.236.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.236.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.237.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.237.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.238.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.238.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.239.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.239.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.240.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.240.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.241.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.241.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.242.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.242.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.243.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.243.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.244.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.244.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.245.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.245.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.246.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.246.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.247.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.247.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.248.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.248.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.249.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.249.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.250.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.250.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.251.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.251.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.252.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.252.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.253.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.253.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.254.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.254.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.255.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.17.mlp.experts.255.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.128.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.128.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.129.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.129.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.130.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.130.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.131.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.131.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.132.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.132.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.133.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.133.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.134.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.134.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.135.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.135.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.136.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.136.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.137.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.137.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.138.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.138.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.139.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.139.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.140.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.140.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.141.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.141.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.142.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.142.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.143.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.143.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.144.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.144.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.145.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.145.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.146.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.146.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.147.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.147.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.148.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.148.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.149.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.149.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.150.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.150.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.151.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.151.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.152.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.152.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.153.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.153.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.154.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.154.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.155.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.155.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.156.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.156.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.157.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.157.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.158.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.158.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.159.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.159.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.160.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.160.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.161.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.161.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.162.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.162.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.163.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.163.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.164.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.164.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.165.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.165.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.166.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.166.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.167.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.167.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.168.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.168.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.169.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.169.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.170.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.170.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.171.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.171.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.172.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.172.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.173.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.173.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.174.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.174.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.175.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.175.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.176.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.176.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.177.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.177.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.178.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.178.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.179.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.179.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.180.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.180.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.181.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.181.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.182.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.182.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.183.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.183.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.184.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.184.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.185.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.185.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.186.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.186.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.187.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.187.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.188.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.188.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.189.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.189.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.190.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.190.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.191.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.191.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.192.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.192.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.193.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.193.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.194.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.194.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.195.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.195.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.196.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.196.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.197.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.197.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.198.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.198.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.199.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.199.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.200.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.200.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.201.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.201.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.202.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.202.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.203.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.203.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.204.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.204.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.205.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.205.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.206.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.206.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.207.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.207.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.208.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.208.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.209.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.209.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.210.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.210.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.211.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.211.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.212.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.212.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.213.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.213.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.214.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.214.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.215.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.215.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.216.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.216.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.217.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.217.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.218.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.218.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.219.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.219.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.220.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.220.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.221.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.221.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.222.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.222.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.223.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.223.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.224.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.224.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.225.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.225.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.226.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.226.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.227.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.227.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.228.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.228.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.229.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.229.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.230.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.230.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.231.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.231.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.232.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.232.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.233.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.233.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.234.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.234.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.235.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.235.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.236.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.236.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.237.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.237.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.238.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.238.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.239.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.239.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.240.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.240.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.241.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.241.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.242.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.242.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.243.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.243.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.244.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.244.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.245.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.245.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.246.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.246.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.247.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.247.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.248.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.248.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.249.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.249.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.250.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.250.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.251.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.251.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.252.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.252.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.253.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.253.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.254.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.254.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.255.gate_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.255.up_proj.weight": "model-00012-of-00022.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.128.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.129.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.130.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.131.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.132.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.133.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.134.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.135.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.136.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.137.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.138.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.139.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.140.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.141.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.142.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.143.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.144.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.145.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.146.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.147.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.148.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.149.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.150.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.151.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.152.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.153.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.154.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.155.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.156.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.157.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.158.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.159.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.160.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.161.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.162.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.163.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.164.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.165.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.166.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.167.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.168.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.169.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.170.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.171.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.172.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.173.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.174.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.175.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.176.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.177.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.178.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.179.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.180.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.181.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.182.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.183.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.184.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.185.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.186.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.187.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.188.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.189.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.190.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.191.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.192.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.193.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.194.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.195.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.196.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.197.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.198.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.199.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.200.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.201.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.202.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.203.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.204.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.205.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.206.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.207.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.208.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.209.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.210.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.211.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.212.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.213.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.214.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.215.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.216.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.217.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.218.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.219.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.220.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.221.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.222.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.223.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.224.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.225.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.226.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.227.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.228.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.229.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.230.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.231.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.232.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.233.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.234.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.235.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.236.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.237.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.238.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.239.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.240.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.241.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.242.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.243.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.244.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.245.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.246.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.247.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.248.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.249.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.250.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.251.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.252.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.253.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.254.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.18.mlp.experts.255.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.128.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.129.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.130.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.131.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.132.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.133.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.134.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.135.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.136.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.137.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.138.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.139.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.140.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.141.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.142.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.143.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.144.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.145.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.146.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.147.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.148.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.149.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.150.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.151.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.152.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.153.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.154.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.155.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.156.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.157.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.158.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.159.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.160.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.161.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.162.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.163.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.164.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.165.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.166.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.167.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.168.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.169.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.170.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.171.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.172.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.173.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.174.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.175.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.176.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.177.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.178.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.179.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.180.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.181.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.182.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.183.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.184.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.185.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.186.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.187.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.188.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.189.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.190.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.191.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.192.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.193.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.194.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.195.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.196.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.197.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.198.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.199.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.200.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.201.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.202.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.203.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.204.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.205.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.206.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.207.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.208.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.209.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.210.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.211.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.212.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.213.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.214.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.215.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.216.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.217.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.218.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.219.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.220.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.221.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.222.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.223.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.224.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.225.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.226.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.227.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.228.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.229.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.230.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.231.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.232.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.233.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.234.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.235.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.236.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.237.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.238.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.239.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.240.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.241.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.242.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.243.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.244.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.245.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.246.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.247.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.248.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.249.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.250.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.251.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.252.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.253.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.254.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.255.down_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.128.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.128.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.129.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.129.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.130.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.130.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.131.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.131.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.132.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.132.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.133.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.133.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.134.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.134.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.135.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.135.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.136.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.136.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.137.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.137.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.138.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.138.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.139.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.139.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.140.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.140.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.141.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.141.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.142.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.142.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.143.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.143.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.144.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.144.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.145.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.145.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.146.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.146.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.147.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.147.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.148.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.148.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.149.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.149.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.150.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.150.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.151.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.151.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.152.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.152.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.153.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.153.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.154.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.154.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.155.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.155.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.156.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.156.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.157.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.157.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.158.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.158.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.159.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.159.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.160.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.160.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.161.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.161.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.162.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.162.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.163.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.163.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.164.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.164.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.165.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.165.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.166.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.166.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.167.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.167.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.168.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.168.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.169.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.169.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.170.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.170.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.171.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.171.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.172.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.172.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.173.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.173.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.174.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.174.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.175.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.175.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.176.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.176.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.177.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.177.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.178.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.178.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.179.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.179.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.180.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.180.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.181.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.181.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.182.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.182.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.183.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.183.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.184.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.184.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.185.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.185.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.186.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.186.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.187.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.187.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.188.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.188.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.189.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.189.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.190.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.190.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.191.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.191.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.192.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.192.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.193.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.193.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.194.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.194.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.195.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.195.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.196.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.196.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.197.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.197.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.198.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.198.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.199.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.199.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.200.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.200.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.201.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.201.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.202.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.202.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.203.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.203.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.204.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.204.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.205.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.205.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.206.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.206.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.207.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.207.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.208.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.208.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.209.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.209.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.210.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.210.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.211.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.211.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.212.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.212.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.213.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.213.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.214.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.214.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.215.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.215.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.216.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.216.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.217.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.217.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.218.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.218.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.219.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.219.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.220.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.220.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.221.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.221.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.222.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.222.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.223.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.223.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.224.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.224.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.225.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.225.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.226.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.226.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.227.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.227.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.228.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.228.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.229.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.229.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.230.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.230.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.231.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.231.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.232.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.232.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.233.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.233.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.234.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.234.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.235.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.235.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.236.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.236.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.237.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.237.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.238.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.238.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.239.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.239.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.240.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.240.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.241.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.241.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.242.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.242.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.243.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.243.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.244.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.244.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.245.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.245.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.246.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.246.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.247.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.247.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.248.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.248.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.249.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.249.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.250.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.250.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.251.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.251.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.252.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.252.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.253.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.253.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.254.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.254.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.255.gate_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.19.mlp.experts.255.up_proj.weight": "model-00013-of-00022.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.128.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.129.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.130.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.131.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.132.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.133.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.134.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.135.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.136.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.137.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.138.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.139.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.140.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.141.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.142.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.143.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.144.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.145.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.146.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.147.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.148.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.149.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.150.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.151.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.152.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.153.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.154.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.155.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.156.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.157.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.158.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.159.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.160.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.161.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.162.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.163.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.164.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.165.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.166.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.167.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.168.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.169.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.170.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.171.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.172.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.173.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.174.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.175.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.176.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.177.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.178.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.179.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.180.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.181.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.182.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.183.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.184.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.185.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.186.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.187.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.188.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.189.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.190.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.191.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.192.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.193.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.194.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.195.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.196.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.197.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.198.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.199.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.200.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.201.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.202.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.203.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.204.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.205.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.206.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.207.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.208.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.209.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.210.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.211.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.212.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.213.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.214.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.215.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.216.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.217.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.218.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.219.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.220.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.221.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.222.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.223.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.224.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.225.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.226.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.227.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.228.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.229.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.230.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.231.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.232.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.233.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.234.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.235.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.236.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.237.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.238.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.239.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.240.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.241.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.242.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.243.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.244.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.245.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.246.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.247.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.248.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.249.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.250.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.251.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.252.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.253.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.254.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.255.down_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.128.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.128.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.129.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.129.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.130.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.130.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.131.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.131.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.132.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.132.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.133.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.133.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.134.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.134.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.135.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.135.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.136.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.136.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.137.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.137.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.138.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.138.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.139.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.139.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.140.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.140.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.141.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.141.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.142.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.142.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.143.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.143.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.144.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.144.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.145.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.145.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.146.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.146.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.147.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.147.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.148.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.148.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.149.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.149.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.150.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.150.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.151.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.151.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.152.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.152.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.153.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.153.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.154.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.154.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.155.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.155.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.156.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.156.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.157.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.157.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.158.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.158.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.159.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.159.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.160.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.160.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.161.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.161.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.162.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.162.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.163.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.163.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.164.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.164.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.165.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.165.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.166.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.166.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.167.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.167.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.168.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.168.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.169.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.169.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.170.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.170.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.171.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.171.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.172.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.172.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.173.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.173.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.174.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.174.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.175.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.175.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.176.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.176.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.177.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.177.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.178.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.178.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.179.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.179.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.180.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.180.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.181.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.181.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.182.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.182.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.183.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.183.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.184.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.184.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.185.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.185.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.186.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.186.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.187.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.187.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.188.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.188.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.189.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.189.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.190.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.190.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.191.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.191.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.192.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.192.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.193.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.193.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.194.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.194.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.195.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.195.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.196.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.196.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.197.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.197.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.198.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.198.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.199.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.199.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.200.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.200.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.201.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.201.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.202.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.202.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.203.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.203.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.204.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.204.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.205.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.205.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.206.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.206.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.207.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.207.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.208.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.208.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.209.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.209.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.210.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.210.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.211.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.211.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.212.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.212.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.213.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.213.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.214.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.214.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.215.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.215.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.216.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.216.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.217.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.217.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.218.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.218.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.219.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.219.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.220.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.220.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.221.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.221.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.222.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.222.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.223.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.223.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.224.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.224.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.225.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.225.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.226.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.226.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.227.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.227.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.228.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.228.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.229.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.229.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.230.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.230.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.231.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.231.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.232.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.232.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.233.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.233.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.234.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.234.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.235.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.235.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.236.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.236.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.237.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.237.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.238.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.238.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.239.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.239.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.240.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.240.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.241.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.241.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.242.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.242.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.243.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.243.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.244.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.244.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.245.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.245.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.246.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.246.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.247.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.247.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.248.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.248.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.249.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.249.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.250.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.250.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.251.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.251.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.252.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.252.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.253.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.253.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.254.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.254.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.255.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.21.mlp.experts.255.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.128.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.128.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.129.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.129.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.130.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.130.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.131.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.131.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.132.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.132.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.133.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.133.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.134.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.134.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.135.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.135.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.136.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.136.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.137.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.137.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.138.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.138.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.139.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.139.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.140.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.140.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.141.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.141.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.142.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.142.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.143.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.143.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.144.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.144.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.145.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.145.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.146.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.146.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.147.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.147.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.148.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.148.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.149.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.149.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.150.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.150.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.151.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.151.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.152.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.152.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.153.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.153.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.154.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.154.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.155.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.155.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.156.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.156.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.157.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.157.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.158.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.158.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.159.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.159.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.160.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.160.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.161.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.161.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.162.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.162.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.163.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.163.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.164.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.164.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.165.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.165.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.166.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.166.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.167.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.167.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.168.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.168.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.169.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.169.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.170.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.170.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.171.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.171.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.172.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.172.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.173.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.173.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.174.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.174.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.175.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.175.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.176.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.176.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.177.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.177.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.178.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.178.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.179.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.179.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.180.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.180.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.181.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.181.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.182.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.182.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.183.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.183.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.184.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.184.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.185.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.185.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.186.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.186.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.187.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.187.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.188.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.188.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.189.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.189.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.190.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.190.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.191.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.191.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.192.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.192.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.193.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.193.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.194.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.194.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.195.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.195.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.196.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.196.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.197.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.197.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.198.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.198.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.199.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.199.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.200.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.200.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.201.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.201.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.202.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.202.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.203.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.203.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.204.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.204.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.205.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.205.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.206.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.206.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.207.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.207.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.208.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.208.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.209.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.209.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.210.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.210.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.211.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.211.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.212.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.212.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.213.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.213.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.214.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.214.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.215.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.215.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.216.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.216.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.217.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.217.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.218.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.218.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.219.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.219.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.220.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.220.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.221.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.221.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.222.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.222.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.223.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.223.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.224.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.224.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.225.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.225.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.226.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.226.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.227.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.227.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.228.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.228.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.229.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.229.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.230.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.230.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.231.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.231.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.232.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.232.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.233.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.233.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.234.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.234.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.235.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.235.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.236.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.236.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.237.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.237.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.238.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.238.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.239.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.239.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.240.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.240.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.241.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.241.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.242.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.242.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.243.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.243.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.244.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.244.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.245.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.245.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.246.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.246.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.247.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.247.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.248.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.248.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.249.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.249.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.250.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.250.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.251.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.251.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.252.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.252.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.253.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.253.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.254.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.254.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.255.gate_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.20.mlp.experts.255.up_proj.weight": "model-00014-of-00022.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.128.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.128.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.129.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.129.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.130.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.130.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.131.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.131.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.132.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.132.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.133.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.133.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.134.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.134.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.135.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.135.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.136.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.136.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.137.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.137.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.138.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.138.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.139.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.139.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.140.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.140.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.141.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.141.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.142.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.142.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.143.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.143.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.144.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.144.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.145.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.145.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.146.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.146.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.147.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.147.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.148.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.148.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.149.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.149.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.150.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.150.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.151.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.151.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.152.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.152.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.153.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.153.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.154.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.154.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.155.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.155.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.156.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.156.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.157.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.157.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.158.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.158.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.159.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.159.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.160.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.160.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.161.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.161.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.162.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.162.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.163.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.163.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.164.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.164.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.165.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.165.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.166.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.166.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.167.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.167.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.168.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.168.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.169.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.169.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.170.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.170.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.171.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.171.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.172.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.172.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.173.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.173.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.174.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.174.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.175.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.175.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.176.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.176.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.177.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.177.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.178.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.178.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.179.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.179.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.180.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.180.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.181.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.181.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.182.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.182.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.183.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.183.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.184.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.184.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.185.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.185.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.186.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.186.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.187.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.187.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.188.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.188.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.189.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.189.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.190.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.190.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.191.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.191.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.192.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.192.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.193.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.193.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.194.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.194.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.195.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.195.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.196.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.196.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.197.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.197.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.198.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.198.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.199.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.199.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.200.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.200.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.201.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.201.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.202.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.202.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.203.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.203.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.204.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.204.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.205.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.205.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.206.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.206.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.207.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.207.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.208.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.208.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.209.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.209.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.210.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.210.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.211.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.211.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.212.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.212.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.213.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.213.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.214.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.214.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.215.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.215.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.216.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.216.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.217.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.217.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.218.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.218.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.219.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.219.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.220.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.220.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.221.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.221.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.222.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.222.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.223.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.223.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.224.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.224.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.225.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.225.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.226.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.226.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.227.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.227.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.228.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.228.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.229.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.229.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.230.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.230.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.231.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.231.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.232.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.232.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.233.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.233.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.234.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.234.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.235.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.235.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.236.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.236.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.237.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.237.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.238.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.238.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.239.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.239.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.240.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.240.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.241.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.241.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.242.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.242.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.243.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.243.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.244.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.244.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.245.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.245.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.246.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.246.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.247.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.247.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.248.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.248.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.249.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.249.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.250.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.250.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.251.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.251.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.252.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.252.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.253.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.253.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.254.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.254.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.255.gate_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.255.up_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.128.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.129.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.130.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.131.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.132.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.133.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.134.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.135.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.136.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.137.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.138.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.139.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.140.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.141.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.142.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.143.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.144.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.145.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.146.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.147.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.148.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.149.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.150.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.151.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.152.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.153.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.154.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.155.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.156.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.157.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.158.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.159.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.160.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.161.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.162.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.163.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.164.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.165.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.166.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.167.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.168.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.169.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.170.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.171.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.172.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.173.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.174.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.175.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.176.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.177.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.178.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.179.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.180.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.181.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.182.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.183.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.184.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.185.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.186.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.187.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.188.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.189.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.190.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.191.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.192.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.193.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.194.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.195.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.196.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.197.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.198.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.199.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.200.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.201.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.202.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.203.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.204.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.205.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.206.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.207.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.208.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.209.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.210.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.211.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.212.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.213.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.214.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.215.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.216.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.217.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.218.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.219.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.220.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.221.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.222.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.223.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.224.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.225.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.226.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.227.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.228.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.229.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.230.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.231.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.232.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.233.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.234.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.235.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.236.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.237.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.238.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.239.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.240.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.241.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.242.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.243.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.244.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.245.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.246.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.247.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.248.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.249.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.250.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.251.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.252.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.253.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.254.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.21.mlp.experts.255.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.128.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.129.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.130.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.131.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.132.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.133.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.134.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.135.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.136.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.137.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.138.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.139.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.140.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.141.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.142.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.143.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.144.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.145.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.146.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.147.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.148.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.149.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.150.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.151.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.152.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.153.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.154.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.155.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.156.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.157.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.158.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.159.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.160.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.161.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.162.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.163.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.164.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.165.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.166.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.167.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.168.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.169.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.170.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.171.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.172.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.173.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.174.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.175.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.176.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.177.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.178.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.179.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.180.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.181.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.182.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.183.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.184.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.185.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.186.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.187.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.188.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.189.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.190.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.191.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.192.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.193.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.194.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.195.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.196.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.197.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.198.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.199.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.200.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.201.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.202.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.203.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.204.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.205.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.206.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.207.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.208.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.209.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.210.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.211.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.212.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.213.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.214.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.215.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.216.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.217.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.218.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.219.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.220.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.221.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.222.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.223.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.224.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.225.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.226.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.227.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.228.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.229.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.230.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.231.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.232.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.233.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.234.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.235.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.236.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.237.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.238.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.239.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.240.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.241.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.242.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.243.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.244.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.245.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.246.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.247.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.248.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.249.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.250.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.251.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.252.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.253.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.254.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.22.mlp.experts.255.down_proj.weight": "model-00015-of-00022.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.128.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.129.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.130.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.131.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.132.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.133.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.134.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.135.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.136.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.137.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.138.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.139.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.140.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.141.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.142.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.143.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.144.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.145.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.146.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.147.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.148.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.149.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.150.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.151.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.152.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.153.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.154.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.155.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.156.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.157.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.158.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.159.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.160.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.161.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.162.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.163.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.164.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.165.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.166.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.167.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.168.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.169.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.170.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.171.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.172.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.173.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.174.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.175.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.176.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.177.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.178.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.179.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.180.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.181.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.182.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.183.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.184.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.185.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.186.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.187.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.188.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.189.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.190.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.191.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.192.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.193.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.194.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.195.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.196.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.197.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.198.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.199.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.200.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.201.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.202.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.203.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.204.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.205.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.206.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.207.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.208.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.209.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.210.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.211.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.212.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.213.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.214.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.215.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.216.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.217.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.218.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.219.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.220.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.221.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.222.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.223.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.224.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.225.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.226.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.227.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.228.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.229.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.230.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.231.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.232.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.233.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.234.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.235.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.236.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.237.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.238.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.239.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.240.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.241.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.242.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.243.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.244.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.245.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.246.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.247.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.248.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.249.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.250.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.251.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.252.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.253.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.254.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.255.down_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.128.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.128.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.129.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.129.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.130.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.130.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.131.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.131.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.132.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.132.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.133.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.133.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.134.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.134.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.135.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.135.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.136.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.136.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.137.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.137.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.138.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.138.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.139.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.139.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.140.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.140.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.141.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.141.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.142.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.142.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.143.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.143.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.144.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.144.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.145.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.145.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.146.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.146.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.147.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.147.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.148.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.148.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.149.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.149.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.150.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.150.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.151.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.151.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.152.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.152.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.153.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.153.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.154.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.154.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.155.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.155.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.156.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.156.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.157.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.157.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.158.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.158.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.159.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.159.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.160.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.160.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.161.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.161.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.162.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.162.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.163.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.163.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.164.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.164.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.165.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.165.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.166.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.166.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.167.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.167.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.168.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.168.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.169.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.169.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.170.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.170.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.171.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.171.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.172.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.172.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.173.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.173.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.174.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.174.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.175.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.175.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.176.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.176.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.177.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.177.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.178.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.178.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.179.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.179.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.180.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.180.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.181.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.181.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.182.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.182.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.183.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.183.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.184.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.184.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.185.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.185.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.186.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.186.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.187.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.187.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.188.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.188.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.189.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.189.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.190.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.190.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.191.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.191.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.192.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.192.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.193.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.193.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.194.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.194.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.195.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.195.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.196.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.196.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.197.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.197.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.198.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.198.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.199.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.199.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.200.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.200.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.201.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.201.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.202.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.202.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.203.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.203.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.204.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.204.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.205.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.205.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.206.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.206.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.207.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.207.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.208.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.208.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.209.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.209.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.210.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.210.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.211.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.211.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.212.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.212.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.213.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.213.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.214.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.214.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.215.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.215.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.216.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.216.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.217.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.217.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.218.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.218.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.219.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.219.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.220.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.220.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.221.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.221.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.222.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.222.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.223.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.223.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.224.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.224.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.225.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.225.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.226.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.226.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.227.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.227.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.228.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.228.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.229.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.229.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.230.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.230.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.231.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.231.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.232.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.232.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.233.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.233.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.234.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.234.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.235.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.235.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.236.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.236.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.237.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.237.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.238.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.238.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.239.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.239.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.240.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.240.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.241.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.241.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.242.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.242.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.243.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.243.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.244.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.244.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.245.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.245.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.246.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.246.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.247.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.247.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.248.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.248.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.249.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.249.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.250.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.250.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.251.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.251.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.252.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.252.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.253.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.253.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.254.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.254.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.255.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.23.mlp.experts.255.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.128.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.128.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.129.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.129.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.130.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.130.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.131.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.131.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.132.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.132.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.133.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.133.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.134.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.134.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.135.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.135.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.136.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.136.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.137.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.137.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.138.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.138.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.139.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.139.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.140.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.140.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.141.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.141.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.142.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.142.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.143.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.143.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.144.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.144.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.145.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.145.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.146.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.146.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.147.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.147.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.148.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.148.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.149.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.149.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.150.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.150.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.151.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.151.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.152.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.152.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.153.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.153.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.154.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.154.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.155.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.155.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.156.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.156.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.157.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.157.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.158.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.158.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.159.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.159.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.160.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.160.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.161.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.161.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.162.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.162.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.163.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.163.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.164.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.164.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.165.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.165.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.166.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.166.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.167.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.167.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.168.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.168.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.169.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.169.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.170.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.170.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.171.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.171.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.172.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.172.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.173.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.173.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.174.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.174.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.175.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.175.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.176.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.176.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.177.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.177.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.178.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.178.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.179.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.179.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.180.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.180.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.181.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.181.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.182.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.182.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.183.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.183.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.184.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.184.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.185.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.185.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.186.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.186.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.187.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.187.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.188.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.188.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.189.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.189.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.190.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.190.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.191.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.191.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.192.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.192.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.193.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.193.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.194.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.194.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.195.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.195.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.196.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.196.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.197.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.197.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.198.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.198.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.199.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.199.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.200.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.200.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.201.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.201.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.202.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.202.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.203.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.203.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.204.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.204.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.205.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.205.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.206.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.206.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.207.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.207.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.208.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.208.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.209.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.209.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.210.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.210.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.211.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.211.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.212.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.212.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.213.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.213.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.214.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.214.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.215.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.215.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.216.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.216.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.217.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.217.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.218.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.218.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.219.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.219.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.220.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.220.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.221.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.221.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.222.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.222.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.223.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.223.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.224.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.224.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.225.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.225.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.226.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.226.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.227.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.227.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.228.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.228.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.229.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.229.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.230.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.230.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.231.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.231.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.232.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.232.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.233.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.233.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.234.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.234.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.235.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.235.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.236.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.236.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.237.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.237.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.238.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.238.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.239.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.239.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.240.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.240.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.241.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.241.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.242.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.242.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.243.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.243.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.244.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.244.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.245.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.245.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.246.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.246.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.247.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.247.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.248.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.248.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.249.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.249.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.250.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.250.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.251.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.251.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.252.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.252.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.253.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.253.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.254.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.254.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.255.gate_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.255.up_proj.weight": "model-00016-of-00022.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.128.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.129.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.130.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.131.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.132.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.133.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.134.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.135.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.136.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.137.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.138.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.139.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.140.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.141.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.142.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.143.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.144.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.145.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.146.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.147.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.148.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.149.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.150.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.151.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.152.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.153.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.154.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.155.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.156.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.157.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.158.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.159.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.160.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.161.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.162.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.163.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.164.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.165.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.166.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.167.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.168.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.169.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.170.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.171.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.172.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.173.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.174.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.175.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.176.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.177.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.178.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.179.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.180.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.181.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.182.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.183.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.184.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.185.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.186.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.187.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.188.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.189.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.190.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.191.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.192.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.193.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.194.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.195.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.196.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.197.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.198.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.199.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.200.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.201.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.202.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.203.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.204.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.205.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.206.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.207.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.208.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.209.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.210.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.211.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.212.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.213.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.214.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.215.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.216.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.217.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.218.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.219.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.220.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.221.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.222.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.223.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.224.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.225.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.226.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.227.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.228.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.229.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.230.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.231.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.232.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.233.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.234.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.235.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.236.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.237.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.238.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.239.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.240.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.241.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.242.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.243.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.244.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.245.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.246.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.247.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.248.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.249.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.250.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.251.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.252.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.253.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.254.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.24.mlp.experts.255.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.128.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.128.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.129.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.129.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.130.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.130.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.131.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.131.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.132.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.132.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.133.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.133.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.134.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.134.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.135.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.135.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.136.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.136.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.137.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.137.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.138.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.138.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.139.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.139.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.140.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.140.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.141.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.141.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.142.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.142.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.143.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.143.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.144.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.144.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.145.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.145.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.146.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.146.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.147.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.147.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.148.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.148.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.149.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.149.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.150.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.150.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.151.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.151.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.152.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.152.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.153.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.153.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.154.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.154.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.155.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.155.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.156.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.156.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.157.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.157.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.158.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.158.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.159.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.159.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.160.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.160.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.161.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.161.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.162.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.162.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.163.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.163.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.164.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.164.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.165.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.165.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.166.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.166.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.167.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.167.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.168.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.168.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.169.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.169.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.170.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.170.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.171.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.171.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.172.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.172.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.173.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.173.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.174.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.174.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.175.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.175.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.176.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.176.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.177.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.177.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.178.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.178.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.179.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.179.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.180.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.180.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.181.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.181.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.182.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.182.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.183.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.183.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.184.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.184.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.185.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.185.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.186.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.186.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.187.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.187.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.188.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.188.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.189.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.189.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.190.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.190.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.191.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.191.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.192.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.192.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.193.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.193.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.194.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.194.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.195.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.195.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.196.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.196.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.197.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.197.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.198.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.198.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.199.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.199.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.200.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.200.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.201.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.201.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.202.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.202.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.203.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.203.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.204.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.204.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.205.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.205.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.206.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.206.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.207.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.207.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.208.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.208.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.209.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.209.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.210.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.210.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.211.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.211.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.212.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.212.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.213.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.213.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.214.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.214.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.215.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.215.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.216.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.216.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.217.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.217.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.218.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.218.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.219.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.219.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.220.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.220.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.221.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.221.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.222.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.222.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.223.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.223.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.224.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.224.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.225.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.225.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.226.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.226.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.227.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.227.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.228.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.228.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.229.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.229.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.230.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.230.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.231.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.231.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.232.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.232.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.233.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.233.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.234.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.234.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.235.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.235.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.236.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.236.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.237.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.237.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.238.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.238.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.239.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.239.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.240.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.240.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.241.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.241.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.242.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.242.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.243.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.243.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.244.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.244.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.245.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.245.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.246.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.246.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.247.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.247.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.248.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.248.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.249.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.249.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.250.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.250.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.251.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.251.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.252.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.252.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.253.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.253.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.254.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.254.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.255.gate_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.255.up_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.128.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.129.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.130.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.131.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.132.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.133.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.134.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.135.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.136.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.137.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.138.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.139.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.140.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.141.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.142.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.143.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.144.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.145.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.146.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.147.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.148.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.149.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.150.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.151.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.152.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.153.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.154.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.155.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.156.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.157.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.158.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.159.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.160.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.161.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.162.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.163.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.164.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.165.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.166.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.167.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.168.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.169.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.170.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.171.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.172.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.173.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.174.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.175.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.176.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.177.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.178.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.179.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.180.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.181.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.182.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.183.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.184.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.185.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.186.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.187.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.188.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.189.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.190.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.191.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.192.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.193.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.194.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.195.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.196.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.197.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.198.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.199.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.200.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.201.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.202.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.203.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.204.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.205.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.206.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.207.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.208.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.209.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.210.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.211.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.212.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.213.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.214.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.215.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.216.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.217.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.218.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.219.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.220.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.221.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.222.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.223.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.224.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.225.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.226.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.227.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.228.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.229.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.230.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.231.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.232.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.233.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.234.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.235.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.236.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.237.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.238.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.239.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.240.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.241.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.242.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.243.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.244.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.245.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.246.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.247.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.248.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.249.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.250.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.251.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.252.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.253.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.254.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.25.mlp.experts.255.down_proj.weight": "model-00017-of-00022.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.128.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.128.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.129.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.129.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.130.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.130.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.131.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.131.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.132.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.132.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.133.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.133.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.134.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.134.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.135.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.135.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.136.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.136.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.137.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.137.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.138.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.138.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.139.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.139.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.140.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.140.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.141.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.141.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.142.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.142.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.143.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.143.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.144.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.144.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.145.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.145.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.146.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.146.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.147.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.147.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.148.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.148.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.149.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.149.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.150.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.150.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.151.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.151.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.152.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.152.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.153.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.153.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.154.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.154.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.155.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.155.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.156.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.156.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.157.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.157.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.158.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.158.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.159.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.159.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.160.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.160.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.161.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.161.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.162.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.162.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.163.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.163.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.164.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.164.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.165.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.165.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.166.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.166.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.167.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.167.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.168.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.168.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.169.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.169.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.170.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.170.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.171.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.171.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.172.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.172.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.173.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.173.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.174.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.174.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.175.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.175.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.176.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.176.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.177.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.177.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.178.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.178.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.179.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.179.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.180.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.180.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.181.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.181.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.182.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.182.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.183.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.183.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.184.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.184.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.185.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.185.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.186.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.186.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.187.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.187.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.188.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.188.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.189.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.189.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.190.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.190.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.191.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.191.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.192.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.192.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.193.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.193.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.194.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.194.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.195.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.195.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.196.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.196.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.197.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.197.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.198.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.198.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.199.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.199.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.200.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.200.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.201.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.201.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.202.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.202.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.203.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.203.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.204.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.204.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.205.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.205.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.206.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.206.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.207.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.207.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.208.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.208.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.209.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.209.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.210.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.210.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.211.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.211.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.212.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.212.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.213.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.213.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.214.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.214.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.215.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.215.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.216.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.216.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.217.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.217.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.218.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.218.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.219.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.219.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.220.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.220.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.221.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.221.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.222.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.222.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.223.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.223.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.224.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.224.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.225.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.225.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.226.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.226.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.227.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.227.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.228.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.228.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.229.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.229.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.230.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.230.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.231.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.231.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.232.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.232.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.233.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.233.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.234.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.234.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.235.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.235.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.236.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.236.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.237.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.237.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.238.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.238.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.239.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.239.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.240.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.240.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.241.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.241.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.242.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.242.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.243.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.243.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.244.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.244.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.245.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.245.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.246.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.246.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.247.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.247.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.248.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.248.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.249.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.249.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.250.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.250.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.251.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.251.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.252.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.252.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.253.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.253.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.254.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.254.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.255.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.255.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.128.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.128.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.129.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.129.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.130.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.130.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.131.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.131.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.132.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.132.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.133.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.133.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.134.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.134.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.135.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.135.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.136.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.136.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.137.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.137.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.138.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.138.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.139.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.139.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.140.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.140.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.141.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.141.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.142.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.142.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.143.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.143.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.144.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.144.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.145.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.145.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.146.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.146.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.147.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.147.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.148.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.148.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.149.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.149.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.150.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.150.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.151.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.151.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.152.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.152.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.153.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.153.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.154.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.154.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.155.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.155.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.156.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.156.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.157.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.157.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.158.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.158.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.159.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.159.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.160.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.160.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.161.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.161.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.162.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.162.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.163.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.163.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.164.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.164.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.165.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.165.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.166.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.166.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.167.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.167.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.168.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.168.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.169.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.169.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.170.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.170.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.171.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.171.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.172.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.172.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.173.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.173.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.174.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.174.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.175.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.175.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.176.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.176.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.177.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.177.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.178.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.178.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.179.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.179.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.180.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.180.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.181.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.181.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.182.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.182.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.183.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.183.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.184.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.184.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.185.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.185.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.186.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.186.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.187.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.187.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.188.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.188.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.189.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.189.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.190.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.190.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.191.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.191.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.192.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.192.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.193.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.193.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.194.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.194.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.195.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.195.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.196.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.196.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.197.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.197.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.198.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.198.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.199.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.199.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.200.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.200.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.201.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.201.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.202.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.202.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.203.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.203.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.204.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.204.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.205.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.205.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.206.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.206.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.207.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.207.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.208.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.208.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.209.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.209.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.210.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.210.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.211.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.211.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.212.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.212.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.213.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.213.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.214.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.214.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.215.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.215.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.216.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.216.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.217.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.217.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.218.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.218.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.219.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.219.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.220.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.220.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.221.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.221.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.222.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.222.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.223.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.223.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.224.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.224.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.225.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.225.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.226.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.226.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.227.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.227.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.228.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.228.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.229.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.229.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.230.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.230.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.231.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.231.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.232.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.232.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.233.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.233.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.234.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.234.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.235.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.235.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.236.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.236.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.237.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.237.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.238.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.238.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.239.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.239.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.240.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.240.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.241.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.241.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.242.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.242.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.243.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.243.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.244.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.244.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.245.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.245.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.246.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.246.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.247.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.247.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.248.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.248.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.249.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.249.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.250.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.250.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.251.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.251.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.252.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.252.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.253.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.253.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.254.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.254.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.255.gate_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.27.mlp.experts.255.up_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.128.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.129.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.130.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.131.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.132.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.133.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.134.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.135.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.136.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.137.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.138.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.139.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.140.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.141.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.142.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.143.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.144.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.145.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.146.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.147.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.148.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.149.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.150.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.151.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.152.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.153.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.154.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.155.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.156.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.157.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.158.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.159.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.160.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.161.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.162.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.163.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.164.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.165.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.166.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.167.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.168.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.169.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.170.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.171.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.172.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.173.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.174.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.175.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.176.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.177.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.178.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.179.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.180.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.181.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.182.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.183.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.184.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.185.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.186.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.187.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.188.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.189.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.190.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.191.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.192.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.193.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.194.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.195.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.196.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.197.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.198.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.199.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.200.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.201.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.202.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.203.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.204.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.205.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.206.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.207.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.208.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.209.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.210.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.211.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.212.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.213.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.214.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.215.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.216.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.217.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.218.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.219.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.220.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.221.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.222.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.223.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.224.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.225.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.226.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.227.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.228.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.229.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.230.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.231.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.232.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.233.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.234.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.235.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.236.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.237.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.238.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.239.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.240.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.241.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.242.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.243.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.244.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.245.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.246.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.247.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.248.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.249.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.250.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.251.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.252.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.253.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.254.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.26.mlp.experts.255.down_proj.weight": "model-00018-of-00022.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.128.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.128.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.129.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.129.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.130.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.130.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.131.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.131.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.132.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.132.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.133.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.133.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.134.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.134.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.135.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.135.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.136.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.136.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.137.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.137.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.138.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.138.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.139.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.139.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.140.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.140.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.141.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.141.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.142.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.142.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.143.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.143.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.144.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.144.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.145.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.145.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.146.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.146.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.147.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.147.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.148.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.148.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.149.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.149.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.150.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.150.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.151.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.151.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.152.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.152.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.153.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.153.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.154.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.154.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.155.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.155.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.156.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.156.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.157.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.157.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.158.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.158.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.159.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.159.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.160.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.160.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.161.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.161.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.162.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.162.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.163.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.163.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.164.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.164.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.165.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.165.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.166.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.166.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.167.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.167.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.168.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.168.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.169.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.169.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.170.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.170.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.171.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.171.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.172.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.172.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.173.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.173.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.174.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.174.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.175.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.175.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.176.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.176.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.177.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.177.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.178.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.178.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.179.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.179.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.180.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.180.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.181.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.181.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.182.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.182.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.183.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.183.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.184.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.184.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.185.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.185.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.186.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.186.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.187.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.187.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.188.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.188.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.189.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.189.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.190.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.190.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.191.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.191.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.192.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.192.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.193.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.193.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.194.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.194.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.195.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.195.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.196.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.196.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.197.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.197.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.198.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.198.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.199.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.199.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.200.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.200.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.201.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.201.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.202.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.202.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.203.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.203.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.204.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.204.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.205.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.205.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.206.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.206.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.207.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.207.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.208.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.208.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.209.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.209.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.210.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.210.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.211.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.211.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.212.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.212.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.213.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.213.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.214.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.214.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.215.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.215.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.216.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.216.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.217.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.217.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.218.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.218.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.219.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.219.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.220.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.220.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.221.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.221.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.222.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.222.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.223.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.223.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.224.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.224.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.225.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.225.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.226.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.226.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.227.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.227.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.228.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.228.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.229.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.229.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.230.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.230.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.231.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.231.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.232.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.232.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.233.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.233.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.234.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.234.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.235.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.235.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.236.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.236.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.237.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.237.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.238.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.238.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.239.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.239.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.240.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.240.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.241.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.241.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.242.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.242.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.243.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.243.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.244.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.244.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.245.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.245.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.246.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.246.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.247.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.247.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.248.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.248.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.249.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.249.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.250.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.250.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.251.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.251.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.252.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.252.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.253.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.253.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.254.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.254.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.255.gate_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.255.up_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.128.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.129.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.130.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.131.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.132.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.133.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.134.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.135.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.136.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.137.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.138.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.139.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.140.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.141.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.142.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.143.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.144.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.145.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.146.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.147.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.148.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.149.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.150.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.151.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.152.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.153.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.154.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.155.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.156.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.157.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.158.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.159.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.160.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.161.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.162.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.163.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.164.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.165.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.166.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.167.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.168.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.169.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.170.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.171.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.172.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.173.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.174.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.175.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.176.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.177.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.178.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.179.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.180.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.181.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.182.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.183.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.184.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.185.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.186.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.187.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.188.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.189.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.190.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.191.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.192.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.193.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.194.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.195.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.196.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.197.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.198.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.199.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.200.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.201.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.202.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.203.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.204.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.205.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.206.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.207.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.208.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.209.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.210.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.211.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.212.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.213.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.214.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.215.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.216.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.217.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.218.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.219.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.220.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.221.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.222.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.223.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.224.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.225.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.226.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.227.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.228.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.229.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.230.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.231.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.232.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.233.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.234.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.235.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.236.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.237.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.238.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.239.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.240.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.241.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.242.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.243.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.244.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.245.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.246.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.247.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.248.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.249.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.250.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.251.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.252.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.253.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.254.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.28.mlp.experts.255.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.128.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.129.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.130.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.131.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.132.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.133.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.134.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.135.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.136.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.137.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.138.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.139.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.140.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.141.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.142.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.143.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.144.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.145.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.146.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.147.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.148.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.149.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.150.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.151.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.152.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.153.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.154.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.155.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.156.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.157.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.158.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.159.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.160.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.161.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.162.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.163.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.164.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.165.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.166.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.167.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.168.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.169.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.170.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.171.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.172.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.173.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.174.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.175.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.176.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.177.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.178.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.179.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.180.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.181.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.182.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.183.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.184.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.185.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.186.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.187.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.188.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.189.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.190.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.191.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.192.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.193.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.194.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.195.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.196.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.197.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.198.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.199.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.200.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.201.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.202.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.203.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.204.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.205.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.206.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.207.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.208.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.209.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.210.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.211.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.212.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.213.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.214.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.215.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.216.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.217.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.218.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.219.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.220.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.221.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.222.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.223.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.224.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.225.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.226.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.227.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.228.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.229.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.230.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.231.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.232.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.233.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.234.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.235.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.236.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.237.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.238.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.239.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.240.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.241.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.242.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.243.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.244.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.245.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.246.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.247.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.248.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.249.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.250.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.251.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.252.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.253.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.254.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.27.mlp.experts.255.down_proj.weight": "model-00019-of-00022.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.128.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.128.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.129.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.129.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.130.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.130.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.131.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.131.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.132.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.132.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.133.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.133.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.134.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.134.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.135.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.135.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.136.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.136.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.137.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.137.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.138.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.138.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.139.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.139.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.140.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.140.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.141.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.141.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.142.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.142.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.143.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.143.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.144.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.144.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.145.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.145.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.146.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.146.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.147.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.147.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.148.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.148.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.149.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.149.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.150.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.150.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.151.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.151.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.152.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.152.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.153.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.153.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.154.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.154.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.155.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.155.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.156.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.156.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.157.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.157.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.158.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.158.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.159.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.159.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.160.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.160.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.161.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.161.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.162.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.162.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.163.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.163.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.164.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.164.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.165.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.165.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.166.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.166.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.167.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.167.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.168.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.168.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.169.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.169.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.170.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.170.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.171.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.171.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.172.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.172.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.173.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.173.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.174.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.174.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.175.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.175.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.176.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.176.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.177.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.177.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.178.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.178.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.179.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.179.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.180.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.180.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.181.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.181.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.182.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.182.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.183.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.183.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.184.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.184.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.185.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.185.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.186.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.186.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.187.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.187.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.188.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.188.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.189.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.189.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.190.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.190.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.191.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.191.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.192.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.192.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.193.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.193.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.194.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.194.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.195.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.195.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.196.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.196.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.197.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.197.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.198.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.198.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.199.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.199.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.200.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.200.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.201.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.201.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.202.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.202.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.203.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.203.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.204.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.204.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.205.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.205.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.206.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.206.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.207.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.207.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.208.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.208.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.209.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.209.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.210.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.210.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.211.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.211.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.212.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.212.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.213.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.213.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.214.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.214.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.215.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.215.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.216.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.216.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.217.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.217.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.218.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.218.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.219.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.219.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.220.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.220.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.221.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.221.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.222.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.222.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.223.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.223.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.224.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.224.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.225.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.225.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.226.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.226.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.227.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.227.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.228.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.228.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.229.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.229.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.230.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.230.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.231.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.231.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.232.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.232.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.233.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.233.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.234.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.234.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.235.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.235.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.236.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.236.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.237.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.237.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.238.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.238.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.239.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.239.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.240.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.240.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.241.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.241.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.242.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.242.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.243.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.243.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.244.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.244.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.245.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.245.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.246.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.246.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.247.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.247.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.248.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.248.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.249.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.249.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.250.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.250.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.251.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.251.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.252.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.252.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.253.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.253.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.254.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.254.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.255.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.255.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.128.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.128.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.129.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.129.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.130.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.130.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.131.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.131.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.132.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.132.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.133.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.133.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.134.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.134.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.135.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.135.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.136.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.136.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.137.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.137.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.138.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.138.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.139.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.139.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.140.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.140.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.141.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.141.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.142.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.142.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.143.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.143.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.144.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.144.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.145.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.145.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.146.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.146.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.147.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.147.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.148.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.148.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.149.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.149.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.150.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.150.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.151.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.151.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.152.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.152.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.153.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.153.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.154.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.154.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.155.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.155.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.156.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.156.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.157.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.157.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.158.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.158.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.159.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.159.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.160.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.160.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.161.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.161.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.162.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.162.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.163.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.163.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.164.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.164.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.165.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.165.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.166.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.166.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.167.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.167.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.168.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.168.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.169.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.169.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.170.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.170.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.171.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.171.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.172.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.172.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.173.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.173.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.174.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.174.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.175.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.175.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.176.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.176.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.177.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.177.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.178.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.178.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.179.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.179.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.180.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.180.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.181.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.181.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.182.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.182.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.183.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.183.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.184.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.184.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.185.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.185.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.186.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.186.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.187.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.187.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.188.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.188.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.189.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.189.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.190.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.190.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.191.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.191.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.192.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.192.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.193.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.193.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.194.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.194.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.195.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.195.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.196.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.196.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.197.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.197.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.198.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.198.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.199.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.199.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.200.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.200.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.201.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.201.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.202.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.202.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.203.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.203.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.204.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.204.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.205.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.205.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.206.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.206.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.207.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.207.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.208.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.208.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.209.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.209.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.210.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.210.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.211.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.211.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.212.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.212.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.213.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.213.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.214.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.214.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.215.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.215.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.216.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.216.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.217.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.217.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.218.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.218.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.219.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.219.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.220.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.220.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.221.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.221.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.222.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.222.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.223.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.223.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.224.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.224.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.225.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.225.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.226.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.226.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.227.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.227.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.228.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.228.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.229.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.229.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.230.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.230.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.231.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.231.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.232.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.232.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.233.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.233.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.234.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.234.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.235.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.235.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.236.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.236.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.237.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.237.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.238.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.238.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.239.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.239.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.240.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.240.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.241.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.241.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.242.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.242.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.243.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.243.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.244.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.244.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.245.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.245.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.246.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.246.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.247.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.247.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.248.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.248.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.249.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.249.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.250.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.250.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.251.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.251.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.252.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.252.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.253.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.253.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.254.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.254.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.255.gate_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.30.mlp.experts.255.up_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.128.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.129.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.130.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.131.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.132.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.133.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.134.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.135.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.136.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.137.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.138.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.139.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.140.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.141.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.142.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.143.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.144.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.145.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.146.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.147.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.148.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.149.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.150.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.151.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.152.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.153.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.154.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.155.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.156.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.157.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.158.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.159.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.160.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.161.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.162.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.163.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.164.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.165.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.166.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.167.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.168.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.169.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.170.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.171.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.172.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.173.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.174.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.175.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.176.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.177.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.178.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.179.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.180.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.181.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.182.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.183.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.184.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.185.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.186.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.187.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.188.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.189.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.190.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.191.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.192.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.193.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.194.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.195.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.196.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.197.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.198.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.199.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.200.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.201.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.202.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.203.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.204.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.205.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.206.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.207.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.208.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.209.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.210.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.211.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.212.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.213.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.214.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.215.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.216.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.217.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.218.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.219.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.220.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.221.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.222.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.223.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.224.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.225.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.226.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.227.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.228.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.229.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.230.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.231.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.232.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.233.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.234.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.235.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.236.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.237.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.238.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.239.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.240.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.241.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.242.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.243.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.244.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.245.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.246.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.247.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.248.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.249.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.250.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.251.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.252.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.253.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.254.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.29.mlp.experts.255.down_proj.weight": "model-00020-of-00022.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.18.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.128.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.129.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.130.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.131.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.132.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.133.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.134.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.135.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.136.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.137.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.138.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.139.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.140.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.141.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.142.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.143.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.144.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.145.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.146.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.147.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.148.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.149.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.150.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.151.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.152.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.153.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.154.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.155.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.156.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.157.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.158.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.159.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.160.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.161.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.162.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.163.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.164.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.165.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.166.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.167.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.168.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.169.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.170.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.171.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.172.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.173.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.174.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.175.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.176.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.177.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.178.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.179.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.180.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.181.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.182.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.183.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.184.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.185.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.186.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.187.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.188.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.189.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.190.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.191.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.192.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.193.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.194.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.195.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.196.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.197.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.198.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.199.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.200.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.201.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.202.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.203.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.204.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.205.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.206.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.207.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.208.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.209.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.210.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.211.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.212.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.213.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.214.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.215.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.216.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.217.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.218.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.219.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.220.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.221.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.222.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.223.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.224.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.225.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.226.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.227.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.228.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.229.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.230.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.231.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.232.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.233.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.234.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.235.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.236.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.237.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.238.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.239.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.240.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.241.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.242.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.243.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.244.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.245.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.246.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.247.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.248.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.249.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.250.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.251.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.252.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.253.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.254.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.experts.255.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.25.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.19.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.21.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.16.mlp.gate.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.17.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.23.mlp.gate.weight": "model-00021-of-00022.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.128.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.129.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.130.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.131.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.132.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.133.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.134.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.135.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.136.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.137.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.138.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.139.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.140.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.141.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.142.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.143.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.144.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.145.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.146.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.147.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.148.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.149.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.150.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.151.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.152.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.153.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.154.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.155.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.156.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.157.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.158.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.159.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.160.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.161.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.162.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.163.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.164.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.165.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.166.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.167.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.168.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.169.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.170.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.171.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.172.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.173.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.174.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.175.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.176.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.177.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.178.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.179.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.180.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.181.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.182.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.183.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.184.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.185.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.186.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.187.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.188.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.189.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.190.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.191.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.192.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.193.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.194.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.195.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.196.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.197.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.198.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.199.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.200.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.201.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.202.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.203.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.204.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.205.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.206.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.207.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.208.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.209.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.210.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.211.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.212.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.213.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.214.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.215.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.216.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.217.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.218.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.219.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.220.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.221.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.222.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.223.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.224.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.225.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.226.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.227.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.228.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.229.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.230.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.231.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.232.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.233.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.234.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.235.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.236.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.237.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.238.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.239.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.240.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.241.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.242.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.243.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.244.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.245.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.246.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.247.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.248.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.249.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.250.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.251.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.252.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.253.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.254.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.255.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.128.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.128.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.129.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.129.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.130.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.130.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.131.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.131.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.132.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.132.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.133.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.133.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.134.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.134.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.135.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.135.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.136.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.136.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.137.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.137.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.138.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.138.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.139.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.139.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.140.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.140.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.141.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.141.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.142.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.142.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.143.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.143.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.144.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.144.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.145.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.145.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.146.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.146.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.147.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.147.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.148.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.148.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.149.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.149.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.150.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.150.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.151.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.151.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.152.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.152.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.153.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.153.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.154.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.154.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.155.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.155.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.156.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.156.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.157.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.157.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.158.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.158.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.159.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.159.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.160.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.160.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.161.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.161.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.162.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.162.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.163.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.163.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.164.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.164.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.165.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.165.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.166.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.166.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.167.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.167.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.168.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.168.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.169.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.169.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.170.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.170.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.171.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.171.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.172.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.172.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.173.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.173.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.174.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.174.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.175.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.175.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.176.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.176.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.177.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.177.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.178.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.178.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.179.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.179.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.180.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.180.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.181.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.181.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.182.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.182.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.183.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.183.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.184.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.184.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.185.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.185.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.186.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.186.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.187.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.187.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.188.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.188.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.189.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.189.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.190.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.190.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.191.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.191.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.192.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.192.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.193.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.193.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.194.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.194.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.195.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.195.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.196.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.196.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.197.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.197.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.198.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.198.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.199.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.199.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.200.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.200.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.201.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.201.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.202.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.202.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.203.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.203.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.204.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.204.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.205.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.205.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.206.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.206.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.207.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.207.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.208.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.208.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.209.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.209.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.210.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.210.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.211.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.211.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.212.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.212.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.213.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.213.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.214.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.214.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.215.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.215.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.216.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.216.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.217.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.217.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.218.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.218.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.219.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.219.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.220.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.220.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.221.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.221.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.222.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.222.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.223.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.223.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.224.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.224.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.225.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.225.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.226.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.226.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.227.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.227.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.228.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.228.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.229.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.229.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.230.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.230.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.231.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.231.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.232.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.232.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.233.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.233.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.234.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.234.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.235.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.235.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.236.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.236.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.237.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.237.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.238.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.238.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.239.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.239.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.240.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.240.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.241.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.241.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.242.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.242.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.243.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.243.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.244.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.244.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.245.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.245.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.246.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.246.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.247.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.247.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.248.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.248.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.249.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.249.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.250.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.250.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.251.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.251.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.252.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.252.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.253.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.253.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.254.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.254.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.255.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.experts.255.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.20.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.24.mlp.gate.weight": "model-00021-of-00022.safetensors", + "model.layers.27.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.28.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.22.mlp.gate.weight": "model-00021-of-00022.safetensors", + "model.layers.30.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.16.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.20.mlp.gate.weight": "model-00021-of-00022.safetensors", + "model.layers.18.mlp.gate.weight": "model-00021-of-00022.safetensors", + "model.layers.17.mlp.gate.weight": "model-00021-of-00022.safetensors", + "model.layers.19.mlp.gate.weight": "model-00021-of-00022.safetensors", + "model.layers.23.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.28.attention.dense.weight": "model-00021-of-00022.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.26.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.22.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.29.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "lm_head.weight": "model-00021-of-00022.safetensors", + "model.layers.21.mlp.gate.weight": "model-00021-of-00022.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.24.attention.query_key_value.weight": "model-00021-of-00022.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00021-of-00022.safetensors", + "model.layers.30.attention.dense.weight": "model-00021-of-00022.safetensors", + "model.layers.16.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.21.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.24.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.30.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.16.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.19.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.20.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.29.mlp.gate.weight": "model-00022-of-00022.safetensors", + "model.layers.29.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.21.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.28.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.27.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.22.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.norm.weight": "model-00022-of-00022.safetensors", + "model.layers.22.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.20.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.18.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.23.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.29.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.21.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.23.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.26.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.26.mlp.gate.weight": "model-00022-of-00022.safetensors", + "model.layers.25.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.22.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.25.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.25.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.20.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.27.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.27.mlp.gate.weight": "model-00022-of-00022.safetensors", + "model.layers.24.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.16.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.23.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.16.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.19.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.28.mlp.gate.weight": "model-00022-of-00022.safetensors", + "model.layers.25.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.28.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.31.mlp.gate.weight": "model-00022-of-00022.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.29.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.30.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.26.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.17.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.18.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.27.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.26.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.23.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.28.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.30.mlp.gate.weight": "model-00022-of-00022.safetensors", + "model.layers.17.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.27.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.24.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.28.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.29.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.24.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.21.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.22.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.26.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.21.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.19.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.31.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.16.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.30.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.20.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.31.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.18.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.17.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.19.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.18.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.20.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.23.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00022-of-00022.safetensors", + "model.layers.30.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.19.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.18.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.17.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.31.attention.query_key_value.weight": "model-00022-of-00022.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.24.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.25.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.29.input_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.31.attention.key_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.31.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.27.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.26.attention.dense.weight": "model-00022-of-00022.safetensors", + "model.layers.31.attention.query_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", + "model.layers.22.mlp.gate.expert_bias": "model-00022-of-00022.safetensors", + "model.layers.25.mlp.gate.weight": "model-00022-of-00022.safetensors", + "model.layers.17.mlp.gate.expert_bias": "model-00022-of-00022.safetensors" } } \ No newline at end of file