pad embeddings to multiple of 128

config.json

@@ -20,7 +20,7 @@
   "rope_scaling": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.32.1",
   "use_cache": true,
   "vocab_size": 32007
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 32005,
   "eos_token_id": 32006,
   "pad_token_id": 0,
-  "transformers_version": "4.31.0"
+  "transformers_version": "4.32.1"
 }

pytorch_model-00001-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e727d96325e58363249ec93e02202f59036d6b68f796c2a049098875a62652
-size 9852720092
+oid sha256:5693d282af8c41a185c93fc2161e09abb4b5ad39fe9b6328ec55880b0f3ac693
+size 9854698469

pytorch_model-00002-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c612ad81c4448e8dcb6cf27ea517da691dcd9cb024db72c45540e68abbaee4f
-size 9798112992
+oid sha256:7b3276da1edcf36f8bd07bd8bfbb285a5ce273f18576ce80ce1e610b79e870b7
+size 9798108893

pytorch_model-00003-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6909ddaf1a83177d1306e33312075c479c26f5f62b2a5753bb1da120228cdeb4
-size 9965883644
+oid sha256:997faaee1e4f721f3b4741a0a239057d07bfb2a77fd117be93e40a82f5132434
+size 9965880015

pytorch_model-00004-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9708c7a22321bcbdc8d5d6c92de0d9699309d50b20b1cd723e6759525ab0a7b7
-size 9798079504
+oid sha256:237582071bd98134d4c1ace75fc7086be4e1920fd35187c3a887c8a0a84f4c72
+size 9798075429

pytorch_model-00005-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0279705ab247d84ca980d60bc185be693451164096eb25dd46c2aa3501846ddd
-size 9798113032
+oid sha256:12a42ef611c4257826e62f78f68fcc600488f706c036ec03bf6bb992c779207d
+size 9798108873

pytorch_model-00006-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3ac6a0d1cc28f8f8ef33fc3dc8bf1c762f21763cd2defc8ae5d6d19f621b86
-size 9798113056
+oid sha256:209f4136bb1231c7529a479035f64f21af1722c425cfb37cea8324031388a8e9
+size 9798108893

pytorch_model-00007-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93bbec5e1c205bde225fe25fc678b4a767ae4592c1578f6b1f8a9139e7eb6b01
-size 9965883644
+oid sha256:e0ff3dc22f681c9ff60eb0cd8cfbbd871b3abaecbe03d368813dbe069b549150
+size 9965880015

pytorch_model-00008-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f59f0c15338986d18569a8113991170cb360d30de2d649cbe69f41582ee6ee52
-size 9798079504
+oid sha256:109968c469b0558aac423cbf15b286cfbf3a08fed0e6bf840f4ec15428b43f4b
+size 9798075429

pytorch_model-00009-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13dd585ddd5bfbe3ea6308bff39adaaa5d6cc61a2b46864d5adf079977dc4c5f
-size 9798113032
+oid sha256:0921cba072f174d91ba82206899492a2b3b677068dcef36d891aeabbbb016cf0
+size 9798108873

pytorch_model-00010-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d91a65d3e10fb476c765df6c4fc159b7a547032b96c01fa96d6b8075dea763c3
-size 9798113056
+oid sha256:485ab12fdbdcdb14af91b39c337a0f12dc7d96dfe93d15b933c1c411a541c46c
+size 9798108893

pytorch_model-00011-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1077ff350755170569856b6e181ed53ccb28d87e28e57f695beb75973b7d4c
-size 9965883644
+oid sha256:b2fbbed4fbf68dbe0d826f85ed49f15d27aab4932657b6d7b1d593a4df170a9c
+size 9965880015

pytorch_model-00012-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe094728ef37207df7ef2b6a7efd5c2a11081d77657fa9b54f4299b002fb273e
-size 9798079504
+oid sha256:f86559f4aa8330ada47d5d0bd9c6c04cb3ce8675b545a97ea839bc95e05bb441
+size 9798075429

pytorch_model-00013-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a4cdf566d45c2d2f94ca94cbfd09007ef32aa7cd54d9157cb36a095adb18618
-size 9798113032
+oid sha256:7cf245007d308d49fecb28dd5c5e765a486a6cfa24d0c957fa597fc2aa2bc3b5
+size 9798108873

pytorch_model-00014-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ad4b712582397442685feef902c5e5331c2fe625c8079ff4a1595026a1aa17
-size 9496137832
+oid sha256:04d518cd19ec244c0b93dc391c4654281dff721e05f0d6c19a364fedcd0094c7
+size 9496134339

pytorch_model-00015-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656389099e94c6629ddf790f7e997bf26cc18f5eeba19f58ad7e30c29f28e81e
-size 524404101
+oid sha256:70e19f991951f004336ae9af2f9db43ebd901ba1849104b0d58f77e4f213e549
+size 526386090

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 137953546240
+    "total_size": 137957490688
   },
   "weight_map": {
     "lm_head.weight": "pytorch_model-00015-of-00015.bin",
@@ -13,7 +13,6 @@
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
@@ -23,7 +22,6 @@
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -33,7 +31,6 @@
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -43,7 +40,6 @@
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -53,7 +49,6 @@
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -63,7 +58,6 @@
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -73,7 +67,6 @@
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -83,7 +76,6 @@
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
@@ -93,7 +85,6 @@
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -103,7 +94,6 @@
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -113,7 +103,6 @@
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -123,7 +112,6 @@
     "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
@@ -133,7 +121,6 @@
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -143,7 +130,6 @@
     "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
@@ -153,7 +139,6 @@
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -163,7 +148,6 @@
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -173,7 +157,6 @@
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -183,7 +166,6 @@
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -193,7 +175,6 @@
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -203,7 +184,6 @@
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
@@ -213,7 +193,6 @@
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -223,7 +202,6 @@
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -233,7 +211,6 @@
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
@@ -243,7 +220,6 @@
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -253,7 +229,6 @@
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -263,7 +238,6 @@
     "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
-    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -273,7 +247,6 @@
     "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
-    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
@@ -283,7 +256,6 @@
     "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
-    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -293,7 +265,6 @@
     "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
-    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
     "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
     "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -303,7 +274,6 @@
     "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
-    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -313,7 +283,6 @@
     "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
-    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -323,7 +292,6 @@
     "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
-    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -333,7 +301,6 @@
     "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
-    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
@@ -343,7 +310,6 @@
     "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
-    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
@@ -353,7 +319,6 @@
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -363,7 +328,6 @@
     "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
-    "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -373,7 +337,6 @@
     "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
-    "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -383,7 +346,6 @@
     "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
-    "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -393,7 +355,6 @@
     "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
-    "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
@@ -403,7 +364,6 @@
     "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
-    "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -413,7 +373,6 @@
     "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
-    "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
     "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
     "model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -423,7 +382,6 @@
     "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
-    "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -433,7 +391,6 @@
     "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
-    "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -443,7 +400,6 @@
     "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
-    "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -453,7 +409,6 @@
     "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
-    "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -463,7 +418,6 @@
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
     "model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
@@ -473,7 +427,6 @@
     "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
-    "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -483,7 +436,6 @@
     "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
-    "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
     "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
     "model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -493,7 +445,6 @@
     "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
-    "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -503,7 +454,6 @@
     "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
-    "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -513,7 +463,6 @@
     "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
-    "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -523,7 +472,6 @@
     "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
-    "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
@@ -533,7 +481,6 @@
     "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
-    "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -543,7 +490,6 @@
     "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
-    "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
     "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
     "model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -553,7 +499,6 @@
     "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
-    "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -563,7 +508,6 @@
     "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
-    "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -573,7 +517,6 @@
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -583,7 +526,6 @@
     "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
-    "model.layers.60.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -593,7 +535,6 @@
     "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
-    "model.layers.61.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
@@ -603,7 +544,6 @@
     "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
-    "model.layers.62.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -613,7 +553,6 @@
     "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
-    "model.layers.63.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -623,7 +562,6 @@
     "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
-    "model.layers.64.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -633,7 +571,6 @@
     "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
-    "model.layers.65.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -643,7 +580,6 @@
     "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
-    "model.layers.66.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
@@ -653,7 +589,6 @@
     "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
-    "model.layers.67.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -663,7 +598,6 @@
     "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
-    "model.layers.68.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
     "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
     "model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -673,7 +607,6 @@
     "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
-    "model.layers.69.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -683,7 +616,6 @@
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -693,7 +625,6 @@
     "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
-    "model.layers.70.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -703,7 +634,6 @@
     "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
-    "model.layers.71.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -713,7 +643,6 @@
     "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
-    "model.layers.72.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
@@ -723,7 +652,6 @@
     "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
-    "model.layers.73.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -733,7 +661,6 @@
     "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
-    "model.layers.74.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
     "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
     "model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -743,7 +670,6 @@
     "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
-    "model.layers.75.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -753,7 +679,6 @@
     "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
-    "model.layers.76.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -763,7 +688,6 @@
     "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
-    "model.layers.77.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -773,7 +697,6 @@
     "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
-    "model.layers.78.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
@@ -783,7 +706,6 @@
     "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
-    "model.layers.79.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
     "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -793,7 +715,6 @@
     "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
@@ -803,7 +724,6 @@
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
     "model.norm.weight": "pytorch_model-00014-of-00015.bin"
   }

tokenizer.json

@@ -114,12 +114,6 @@
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
@@ -128,24 +122,12 @@
       }
     ],
     "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
       {
         "Sequence": {
           "id": "B",
@@ -153,17 +135,7 @@
         }
       }
     ],
-    "special_tokens": {
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          1
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
+    "special_tokens": {}
   },
   "decoder": {
     "type": "Sequence",

tokenizer_config.json

@@ -30,5 +30,6 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  }
+  },
+  "use_default_system_prompt": false
 }