Extend vocab size from 32000 to 44800, prepare for continued pretrain

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/Users/steve/.cache/huggingface/hub/models--h2oai--h2ogpt-4096-llama2-7b-chat/snapshots/021505756a74d4106d3e18774c4e9ac016eaeee1",
+  "_name_or_path": "F:\\apps\\oobabooga_windows\\text-generation-webui\\models\\vllama2-7b-chat",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -14,13 +14,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.30.0",
+  "transformers_version": "4.34.0.dev0",
   "use_cache": true,
-  "vocab_size": 48281
+  "vocab_size": 44800
 }

generation_config.json

@@ -1,17 +1,6 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 1,
-  "do_sample": true,
   "eos_token_id": 2,
-  "max_length": 4096,
-  "max_memory": {
-    "mps": 24248877056
-  },
-  "no_split_module_classes": [
-    "LlamaDecoderLayer"
-  ],
-  "pad_token_id": 0,
-  "special_dtypes": {},
-  "temperature": 0.6,
-  "top_p": 0.9,
-  "transformers_version": "4.30.0"
+  "transformers_version": "4.34.0.dev0"
 }

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d438829731ab9dd01705bb324342e22b72ef4c805dc459b1500fda587b5394
-size 9964382091
+oid sha256:ace9a7d3c8c20e397832cb46211221111719dcf59a57b2a4c8160fae32e6a6ce
+size 9907343583

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daef3732139dc5c34019ce2b8158a6104c4981a5f034169036c6f58207f7bf37
-size 9894801074
+oid sha256:13e7b1430da5e8d4dcc4de65c06ce5f22e63172a791a2465b7e2d0484ccbbbf9
+size 9894795314

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9784bcfa6f1ed5578b8d67a6ba7b5367a6f42364dc8c2ebc571f8525030aea2
-size 3598898351
+oid sha256:0c97048e2ee1173cc5d7921176ef98cb1939d682fb159e95c37ae8a329495d6a
+size 7571057583

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 24496496640
+    "total_size": 27373092864
   },
   "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-00002-of-00003.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-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-00002-of-00003.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -53,7 +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",
@@ -63,7 +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",
@@ -73,7 +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",
@@ -83,7 +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",
@@ -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-00003-of-00003.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-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-00003-of-00003.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
@@ -183,7 +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",
@@ -193,7 +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",
@@ -203,7 +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",
@@ -213,7 +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",
@@ -223,7 +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",
@@ -233,7 +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",
@@ -243,7 +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",
@@ -253,7 +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",
@@ -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.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
@@ -273,7 +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",
@@ -283,7 +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",
@@ -293,7 +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",
@@ -303,7 +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",
@@ -313,7 +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",
@@ -323,7 +292,6 @@
     "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"
   }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac83ffd7373f321172f657da62d06d8143c0fc37e79d016a06a3a65792b8e921
-size 764959
+oid sha256:794f7bce2336bbec1d131e7f9a070659dd2f15b78ed002b47b907eec8e42c143
+size 708323