Upload checkpoints to main revision

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Olmo2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 4096,
+  "model_type": "olmo2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "pad_token_id": 100277,
+  "transformers_version": "4.47.1"
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4016708ba7f6c242242a9aebebe41d5283d8ba3c14074162fae518c072d01c5b
+size 4823541920

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b9112f2a67068a2f324725159248faf5591e30c4523cdac9c3337e3dd4e844
+size 4467067512

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadc6243821f18f0dd56f7e88c683e2cea91ef3c9e93e97fd04816879b2e3595
+size 4718792208

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d263da5193292bb14993ef4285759bcd84745accf1f922e604b59c796b60a5
+size 4467067512

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f4bb07eda80d1c1c44b291d7cfec80fff2296016a8d20caeeebc8cb49d3627
+size 4467067520

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83674d57a72a6368669d6b212f10d8815836a32e8ac7033d61ea225c04e06599
+size 4718792240

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b1694c6c059f740fea551bf3cb479a0c32d95b1fe189ab00a942e98a0f9347
+size 4467067536

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d5ff62c739f06c90ae5a847dbc5c151806c375ccc798c64d31c22f43824551
+size 4467067528

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f07f9063abdb6b4c9ade00e9ce92beca849f2e9baa0eee31a1ba055a8b1303
+size 4718792240

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feda7deedc9830bd716c9d8b0c8db54dcff0e38dd97a7ea062e9d6e5e3eb709f
+size 4467067536

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d96f74b1f687273efc58a522bd60005fb9a04d24d208cfae86e776a0ad2df9
+size 4467067528

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fbffb435e06cca4acb3c2fdd6c3655b4f6816ddaef40f237dcee27b515b47a
+size 4718792240

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d920239409aa1bf00ec850c3e4b3ca487bd182a79f5c760ccccec342113ea99
+size 4467067536

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b6da470f31806b4c07d8706a1b7dc315dcebabf01b21b0e4450f9dffcbd43b
+size 4467067528

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5323e20ff2078104fd73e4f9e18dae24c2b8b22552be786da50555a29dbf004b
+size 4718792240

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810df0b075332a9394efc0386a163617729b46a39a3fa4ac06e6fa781c5dc26a
+size 4467067536

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a933b6123d526772dfffe94e82fc18f95be70cec12491dfd5e05edec0a7fc0
+size 4467067528

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4314c4f80dfb089ab206350d1c20ae64cc3e2fc9e9c72df04a2548c4ab9c9ee
+size 4718792240

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1158408201e89be236c1722b9d8495b81c68d34d02fb8c15ae021d5df028906
+size 4467067536

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc752f4a5ae1ed48cfc4724a5fc153ce148a58e57eabf5a7907ff284863e4cb
+size 4467067528

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a8815bb6eaba80dd68c892b6d56c09fbb2f79ff1a9027819d6fce94651772b
+size 4718792240

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20326bc353f4cec48869722c5ce7c315c109d1c4a86a637fadd41e2a266bf975
+size 4467067536

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3a7e6c2958d4181633e07266fd8fadb5dc14c3d1b77bc742bf8cfcaef11049
+size 4467067528

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff290550b45c8cbd02bd7fcff367bf73e293793122e0568d930b2a04bb9c0045
+size 4718792240

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e49c2fe381adaa34df4fa9b1486cb2e5b0ce792ff903361fc5bdb654dce4cfe
+size 4467067536

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7eaff0b2741a59878afe93196e4ae01a14e30d90b491f941881d7d2dcf0fcd
+size 4467067528

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b732fcd7e5744e7f3870fba414d355f989793c7533f33b2cf0e314b5675b2e
+size 4718792240

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dcd0c67bca704b0f507dbdb3d96413137d72e5c8f822aa0a1a654d4536175bd
+size 3649173440

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd7b9e2f478e1141011ee0c2c4dac205a0812f7a72ee4b4d22c688ccd8b775e9
+size 2055209088

model.safetensors.index.json

@@ -0,0 +1,714 @@
+{
+  "metadata": {
+    "total_size": 128937119744
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00029-of-00029.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.post_feedforward_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.post_feedforward_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.post_feedforward_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.post_feedforward_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.post_feedforward_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.post_feedforward_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.post_feedforward_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.post_feedforward_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.post_feedforward_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.k_norm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.50.self_attn.q_norm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.post_feedforward_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.k_norm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.q_norm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.post_feedforward_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.self_attn.k_norm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.q_norm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.post_feedforward_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.k_norm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.q_norm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.post_feedforward_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.k_norm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.q_norm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.post_feedforward_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.k_norm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.55.self_attn.q_norm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.post_feedforward_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.k_norm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.q_norm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.post_feedforward_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.k_norm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.57.self_attn.q_norm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.post_feedforward_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.k_norm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.q_norm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.post_feedforward_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.self_attn.k_norm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.q_norm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.post_feedforward_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.k_norm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.q_norm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.post_feedforward_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.k_norm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.q_norm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.post_feedforward_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.k_norm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.62.self_attn.q_norm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.post_feedforward_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.k_norm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.q_norm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.norm.weight": "model-00028-of-00029.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}