Add v2.0 chat model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "_name_or_path": "outputs/chat/llama-2-7b-ft-chat-max2048-packing2048-ep3-bs128-lr1e4-gpt3_5data-merged",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -14,7 +14,6 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

generation_config.json

@@ -1,9 +1,10 @@
 {
   "bos_token_id": 1,
+  "do_sample": true,
   "eos_token_id": 2,
   "max_length": 4096,
   "pad_token_id": 0,
-  "temperature": 0.9,
-  "top_p": 0.6,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.32.0.dev0"
 }

pytorch_model-00001-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75571f71b16ce3011e3fc014bd466e43b01c393db7cb037e98bc4af10c00a440
-size 1981889895
+oid sha256:598f272292e5fd95a1b8c55661f75e8cd723e7c03261e3a3c87d419b2d02d2db
+size 1981887519

pytorch_model-00002-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4d5007776fabc16447294ce807bd2afd8f23061090c505855775cc7a19c5ac
-size 1990296833
+oid sha256:0c601f9ad5961862c6d33b2ce20a87fa4faace97a0bf15f15c79c25ef8d83759
+size 1990293863

pytorch_model-00003-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441a79ebeba2240f5fbe5f35227384fb7bf80cf52ecbdc46d1a6a2ec09f2602f
-size 1990296833
+oid sha256:bd5c437796e4ff0d52f09d6285284c05a39b11771c4ab20d323ce2ca0d2f14be
+size 1990293863

pytorch_model-00004-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c950468e60d4dc7bb9dee7bf4bf702f70d56f7229cc5edc97da7376e72d21cec
-size 1990296897
+oid sha256:63a461d1338d87ff5b300b99a94be2387eba61bdf0583b4b1dc7a5bc98193f4b
+size 1990293863

pytorch_model-00005-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4414099a8aeb38dfefd34d0c527696d64d2b9c0216aadc2e4b234f1fa218cbc
-size 1933656733
+oid sha256:e586d815091d3fe896b493e5c6205216a58c5c0eb404bc6736e0093f04390cff
+size 1933653763

pytorch_model-00006-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18924e3957da56af10f925fcd5cbcb8835728e339da5c26217ed9556af7328cf
-size 1933673793
+oid sha256:c96192318a0c5cf3fd5939b121cb84d3377bb38b6f5a1650853e544b101e84a5
+size 1933670759

pytorch_model-00007-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0dcaa5c68f30eaaa78be05dab5f1a9e49dc6bdedd22efdbd03c8a5138075183
-size 1656836567
+oid sha256:b6bd313fae56049023afba7dcdc334fe3fb73fbfabe35bf9647d2e602e98fbf1
+size 1656834785

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13476839424
+    "total_size": 13476831232
   },
   "weight_map": {
     "lm_head.weight": "pytorch_model-00007-of-00007.bin",
@@ -13,7 +13,6 @@
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
@@ -23,7 +22,6 @@
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -33,7 +31,6 @@
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -43,7 +40,6 @@
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -53,7 +49,6 @@
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -63,7 +58,6 @@
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -73,7 +67,6 @@
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -83,7 +76,6 @@
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -93,7 +85,6 @@
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -103,7 +94,6 @@
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -113,7 +103,6 @@
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -123,7 +112,6 @@
     "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
@@ -133,7 +121,6 @@
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -143,7 +130,6 @@
     "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -153,7 +139,6 @@
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -163,7 +148,6 @@
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -173,7 +157,6 @@
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -183,7 +166,6 @@
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -193,7 +175,6 @@
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -203,7 +184,6 @@
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -213,7 +193,6 @@
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -223,7 +202,6 @@
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -233,7 +211,6 @@
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
@@ -243,7 +220,6 @@
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -253,7 +229,6 @@
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -263,7 +238,6 @@
     "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -273,7 +247,6 @@
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -283,7 +256,6 @@
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -293,7 +265,6 @@
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -303,7 +274,6 @@
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -313,7 +283,6 @@
     "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -323,7 +292,6 @@
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.norm.weight": "pytorch_model-00007-of-00007.bin"
   }