Upload LlamaForCausalLM

config.json

@@ -1,26 +1,28 @@
 {
-  "_name_or_path": "tigerbot-70b-chat-v2",
+  "_name_or_path": "models/tigerbot-70b-chat-v6-group-ckpt-3000/",
   "architectures": [
     "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 8192,
   "initializer_range": 0.02,
   "intermediate_size": 28672,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
   "num_key_value_heads": 8,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
+  "pad_token_id": 65109,
+  "pretraining_tp": 4,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 10000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.34.0",
   "use_cache": true,
-  "vocab_size": 60515
+  "vocab_size": 65112
 }

generation_config.json

@@ -1,9 +1,7 @@
 {
-  "do_sample": true,
+  "_from_model_config": true,
+  "bos_token_id": 1,
   "eos_token_id": 2,
-  "max_length": 1024,
-  "pad_token_id": 60514,
-  "repetition_penalty": 1.06,
-  "temperature": 0.2,
-  "transformers_version": "4.31.0"
+  "pad_token_id": 65109,
+  "transformers_version": "4.34.0"
 }

pytorch_model-00001-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02823961bf4f9813cb2f971868a23c58e86e5a52290c99c2009a92a0438cf729
-size 9850032363
+oid sha256:c63cb2218cc721d67b243058fe5a9c031bad51e5742524b3e984bb02fa25609d
+size 9925346498

pytorch_model-00002-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9871fea668d1f364b79633129d1ed29b028c652087671a13e2b4243f5e451fc5
-size 9965883093
+oid sha256:8848e0864abedc8fa34a381c34cd391823154cf37b5a7a664c7a97129acd1a9f
+size 9965880502

pytorch_model-00003-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3bd792d39b5fd1e2506013923cbd6407b681044fe71e8885aad5ed5eb341951
-size 9798079017
+oid sha256:a5bff3b41355ecc841749bcfa877cc935d9045b888b45926fb20e6b3649b4975
+size 9798075916

pytorch_model-00004-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8649269c49baf529c24c1833067f8a462af94992250d6d0e720715973c1141d
-size 9798112545
+oid sha256:ea94c699ef66ed027c63cbb28160388172bb152206592a85ecfb29a6b16f433d
+size 9798109360

pytorch_model-00005-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc2dcf1291fd8f9a00818c9cce5448248429c5eda40916b1acd48937ecf2178
-size 9798112569
+oid sha256:26867bda9c1cc51a6008373b42664741edfc9e9952b774ab72c33a4cc030530a
+size 9798109444

pytorch_model-00006-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b635de3b752f53ee9f7aff41415d4a8e2b28a0102ce795afdfa5e377c7ce7844
-size 9965883157
+oid sha256:84a5846fb34c2479872deed941ee659a635bbaace708d940d9cc524bda1f55cf
+size 9965880502

pytorch_model-00007-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e17c02a808cdc711d10fe6285213dd95cbc2603b63950fe5f6adaff16a2e5f
-size 9798079017
+oid sha256:920b53960882274f0217aea3e029c7f02dfb8cc6cc5b661722099f5730d683a5
+size 9798075916

pytorch_model-00008-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb715b9bbe452c63676e81b44f47b92dd48215b43783dba7c84c3ef35f01e55
-size 9798112545
+oid sha256:2a38352e499bc3dbfc2117d6e784eb2867d511750d6aaaa249a298d5e772a929
+size 9798109360

pytorch_model-00009-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cee7dff644dc40949242f43ad61ece41c049c303e4c9645576f2ef1518ca2a9
-size 9798112569
+oid sha256:6eb50eecd16840ddb7831a253650a3cbbfb85443f6d55cd804ccfe4468f9cff7
+size 9798109444

pytorch_model-00010-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec628b661cf385e1ecf80add7121c4d76f66a86912523f21daa4ffd34eab2f3
-size 9965883157
+oid sha256:db271d776a05a46a66f1e6044aaa638f5f90bd3d1e66030192892b77d4b53ddd
+size 9965880502

pytorch_model-00011-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ba38b54c848720a0f4ad89d1bc6040d46caf232554abc0fcaa841ccab69418a
-size 9798079017
+oid sha256:19e5dd361ae30a701a16c4eeb18291120508f9d8fccc58732496363827329ad0
+size 9798075916

pytorch_model-00012-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56dd9a97dcbf7a9f1d3a424b94304705745b95fb85c2875c552ae41489850e61
-size 9798112545
+oid sha256:0005383b36ee391fb959b7f123b363009706ed30ee039ff8bc9443480f9c51d6
+size 9798109360

pytorch_model-00013-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:061bbc6af36bdbd498017e9d079b2e248ff147bdfe2bd3a2da9940350392df29
-size 9798112569
+oid sha256:95583422f5225400cbde65151bf3c6cdbab9b7a5f071ad1425149b8e8cf4c24e
+size 9798109444

pytorch_model-00014-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916dcbdf7cc6b2c5e1e0bf83f7825d32255218377a2188a8fd9b00e2598dce3f
-size 9965899827
+oid sha256:31bd12518e9f91ce6863e8b25465faeab5c7c9104f83eeb457985e55f0db6d2a
+size 9965897236

pytorch_model-00015-of-00015.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c4c4c3ac21cdfc8e7783f284ab6055b5a382cbe6cf4c53c6458e3432941128
-size 991478698
+oid sha256:2fac447d8622e003d25aa1b2eb223afed7b914d60abf12c0264b05d61de0ba1e
+size 1066796421

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 138887696384
+    "total_size": 139038310400
   },
   "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-00003-of-00015.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-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-00004-of-00015.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-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-00007-of-00015.bin",
     "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
     "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
-    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
     "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00007-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-00008-of-00015.bin",
     "model.layers.39.mlp.down_proj.weight": "pytorch_model-00008-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-00011-of-00015.bin",
     "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
     "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
-    "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
     "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00011-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-00012-of-00015.bin",
     "model.layers.62.mlp.down_proj.weight": "pytorch_model-00012-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"
   }