Upload LlamaForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "/ibex/user/xuj0h/LLM_ckpt/llama-pretrained-RLHF-v1.0",
   "architectures": [
-    "LlamaForSequenceClassification"
+    "LlamaForCausalLM"
   ],
   "bos_token_id": 1,
   "dropout": 0.0,
@@ -21,9 +21,10 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.33.2",
   "use_cache": true,
   "vocab_size": 32000
 }

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362d77a8061d5512514c87838c947f3760c37695c422090abbb67231c2d6c408
-size 9877989586
+oid sha256:76e19aaac660ce23de498209ffb5eed9bbb5f98c78aaa2cddeee4b47e3f35a92
+size 9877982386

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407c0d4b3a1f29fe454be0921cb3c418c97c9c711993c53d79bcd80300ea5246
-size 9894801014
+oid sha256:18a728107f56210a16030188869a82c3eeff410faa8f85c1da19407453adbdac
+size 9894793766

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29ecc896e9b663701b24476aff1c92e755d0f32729adc43992eba9882fd73134
-size 6656735417
+oid sha256:0a95ec12ac0b4513069dbefd6b73de00ff7b6b45718172681942fc1b172b744b
+size 7180985861

pytorch_model.bin.index.json

@@ -1,8 +1,9 @@
 {
   "metadata": {
-    "total_size": 26429415424
+    "total_size": 26953662464
   },
   "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
     "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -12,7 +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",
@@ -22,7 +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",
@@ -32,7 +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-00002-of-00003.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -42,7 +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-00002-of-00003.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -52,7 +49,6 @@
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -62,7 +58,6 @@
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -72,7 +67,6 @@
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-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",
@@ -82,7 +76,6 @@
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-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-00002-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",
@@ -92,7 +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",
@@ -102,7 +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",
@@ -112,7 +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",
@@ -122,7 +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",
@@ -132,7 +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",
@@ -142,7 +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",
@@ -152,7 +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",
@@ -162,17 +148,15 @@
     "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-00003-of-00003.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "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-00003-of-00003.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -182,7 +166,6 @@
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -192,7 +175,6 @@
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -202,7 +184,6 @@
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -212,7 +193,6 @@
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -222,7 +202,6 @@
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -232,7 +211,6 @@
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-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",
@@ -242,7 +220,6 @@
     "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-00003-of-00003.bin",
@@ -252,7 +229,6 @@
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-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",
@@ -262,7 +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.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -272,7 +247,6 @@
     "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",
@@ -282,7 +256,6 @@
     "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",
@@ -292,7 +265,6 @@
     "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",
@@ -302,7 +274,6 @@
     "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",
@@ -312,7 +283,6 @@
     "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",
@@ -322,9 +292,7 @@
     "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",
-    "score.weight": "pytorch_model-00003-of-00003.bin"
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
   }
 }