Upload LlamaForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "/ibex/user/xuj0h/LLM_ckpt/llama-pretrained-13b-RLHF-1199",
   "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-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e7edaf2a32a0ff29e90a003b1c1c3aa2b625c2266560a7c32cdf69e6be22a1
-size 9956543883
+oid sha256:b41cdb598298aec954b2611b8bad6a2fe9693af40b60ac7a61ba670a0efc445c
+size 9956539083

pytorch_model-00002-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:904a4e04e47805b0f4492f7672eabf4557b0a95634866af61b75ddeca0ddf525
-size 9940856385
+oid sha256:e2e1a126036c941e42895ea09da0ca1ababa3f687a637e5464e157d3ed1e7a43
+size 9940852143

pytorch_model-00003-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dbc0f8a27418bf3ae4ee365835864d9a50975f3ab271b13dd50da4b645a1336
-size 9940856943
+oid sha256:edeac1745efffdc7f803f92463d5ba0a78c1b1560906df0144e3571d4d3bfd3f
+size 9940852155

pytorch_model-00004-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c82ea85c038872e699c50287d87fc87e513931c8890eba27944ed5f87e73443
-size 9867415289
+oid sha256:9f056f065cb0bb39ac5c29768ad676fdeb58fa7ed04ba56dad673dbf70fb1d18
+size 9867410489

pytorch_model-00005-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9409e501a13b410ba61e562eec1ff2f081d4c43542fc2a67de7bc0e8a77138
-size 9867456961
+oid sha256:f0ed5d10ddf731f62c8d9c0ad1d160b0539ff5b8e44cbaf518b4a6574ed9f3f1
+size 9867452125

pytorch_model-00006-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6a0d33d0b1b43ed5db2dd743733e1ce9cf00ac622570e6587dffb5810a542b
-size 1835157167
+oid sha256:647ac63714d52a4fcd21cd902c89362c40bc0632baa89a918eeb34704441eec1
+size 2490475677

pytorch_model.bin.index.json

@@ -1,8 +1,9 @@
 {
   "metadata": {
-    "total_size": 51408148480
+    "total_size": 52063457280
   },
   "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
     "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
@@ -12,7 +13,6 @@
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
@@ -22,7 +22,6 @@
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
@@ -32,7 +31,6 @@
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
@@ -42,7 +40,6 @@
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
@@ -52,7 +49,6 @@
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
@@ -62,7 +58,6 @@
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
@@ -72,7 +67,6 @@
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
@@ -82,7 +76,6 @@
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
@@ -92,7 +85,6 @@
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
@@ -102,7 +94,6 @@
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
@@ -112,7 +103,6 @@
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
@@ -122,7 +112,6 @@
     "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
     "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
@@ -132,7 +121,6 @@
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
@@ -142,7 +130,6 @@
     "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
     "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
@@ -152,7 +139,6 @@
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
@@ -162,7 +148,6 @@
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
@@ -172,7 +157,6 @@
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
@@ -182,7 +166,6 @@
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
@@ -192,7 +175,6 @@
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
@@ -202,7 +184,6 @@
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
@@ -212,7 +193,6 @@
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
@@ -222,7 +202,6 @@
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
@@ -232,7 +211,6 @@
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
@@ -242,17 +220,15 @@
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
     "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
@@ -262,7 +238,6 @@
     "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
     "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
@@ -272,7 +247,6 @@
     "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
     "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
@@ -282,7 +256,6 @@
     "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
     "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
@@ -292,7 +265,6 @@
     "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
     "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
@@ -302,7 +274,6 @@
     "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
     "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
@@ -312,7 +283,6 @@
     "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
     "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
@@ -322,7 +292,6 @@
     "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
     "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
     "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
@@ -332,7 +301,6 @@
     "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
     "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
     "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
     "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
@@ -342,7 +310,6 @@
     "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
     "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
     "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
     "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
@@ -352,7 +319,6 @@
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
@@ -362,7 +328,6 @@
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
@@ -372,7 +337,6 @@
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
@@ -382,7 +346,6 @@
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
@@ -392,7 +355,6 @@
     "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
     "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
@@ -402,9 +364,7 @@
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "model.norm.weight": "pytorch_model-00006-of-00006.bin",
-    "score.weight": "pytorch_model-00006-of-00006.bin"
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
   }
 }