Upload LlamaForCausalLM

config.json

@@ -1,8 +1,9 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -14,13 +15,13 @@
   "num_attention_heads": 40,
   "num_hidden_layers": 40,
   "num_key_value_heads": 40,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.34.0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,10 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
+  "do_sample": true,
   "eos_token_id": 2,
+  "max_length": 4096,
   "pad_token_id": 0,
-  "transformers_version": "4.28.1"
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.34.0"
 }

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f1021119a9062174537b9985b95b432affc675e74848073f9feb21f0196cc79
-size 9948728430
+oid sha256:ad22de701ec1e455741d5bbfac43cb5dc101ebdad5ede8478622978f45307964
+size 9948719433

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c04463e060781b5e8ccfcdb58f1f282a5deb367165d5fc9d6a5ad410963b54
-size 9904165024
+oid sha256:942c52e0b5a36ddcb7edc96b51c669f688b5f1124bc3331c1d02ebe811b155e0
+size 9904155408

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae17ac4024e67cd1cb13e0ecef055d77a91cf2ab0ee812634cd18c011bd7ed61
-size 6178983625
+oid sha256:019d36b1ec3289e58158b559b6e27281ca2b1c9ead3cb750b238dabfdafbd3ed
+size 6178978207

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 26031738880
+    "total_size": 26031728640
   },
   "weight_map": {
     "lm_head.weight": "pytorch_model-00003-of-00003.bin",
@@ -13,7 +13,6 @@
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -23,7 +22,6 @@
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -33,7 +31,6 @@
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -43,7 +40,6 @@
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -53,7 +49,6 @@
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -63,7 +58,6 @@
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -73,7 +67,6 @@
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -83,7 +76,6 @@
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -93,7 +85,6 @@
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -103,7 +94,6 @@
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -113,7 +103,6 @@
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -123,7 +112,6 @@
     "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -133,7 +121,6 @@
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -143,7 +130,6 @@
     "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -153,7 +139,6 @@
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -163,7 +148,6 @@
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -173,7 +157,6 @@
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -183,7 +166,6 @@
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -193,7 +175,6 @@
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -203,7 +184,6 @@
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -213,7 +193,6 @@
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -223,7 +202,6 @@
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -233,7 +211,6 @@
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -243,17 +220,15 @@
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -263,7 +238,6 @@
     "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -273,7 +247,6 @@
     "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -283,7 +256,6 @@
     "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -293,7 +265,6 @@
     "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -303,7 +274,6 @@
     "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -313,7 +283,6 @@
     "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -323,7 +292,6 @@
     "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -333,7 +301,6 @@
     "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -343,7 +310,6 @@
     "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -353,7 +319,6 @@
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -363,7 +328,6 @@
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -373,7 +337,6 @@
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -383,7 +346,6 @@
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -393,7 +355,6 @@
     "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -403,7 +364,6 @@
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.norm.weight": "pytorch_model-00003-of-00003.bin"
   }