upgrade model

config.json

@@ -1,10 +1,10 @@
 {
-  "_name_or_path": "/gruntdata/code_gpt_nas/user/166675/model/base_model/codellama-7b-hf",
+  "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "bos_token_id": 1,
-  "eos_token": "</s>",
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
@@ -15,15 +15,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pad_token": "<unk>",
-  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.33.2",
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 32016
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.33.2"
+  "transformers_version": "4.34.1"
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad805db998ce3cbc835746fd9bd736bdf94cff8a1157bc689190221451554015
-size 9976754202
+oid sha256:f4c481b74ee79fd231d00e2b2671a5e56bd122725bd68a4e6fe3fbfb1a532e78
+size 9976751681

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3286276574c69f07784d41de0fb4c27e56806d977a9df78d9e31d481a0f9f12
-size 3500442883
+oid sha256:e3e3d7d94bb4afd731407ec5d0797fcc075d88214fe9cb5d41fa20d099902103
+size 3500442334

tokenizer_config.json

@@ -1,33 +1,43 @@
 {
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "legacy": null,
+  "eos_token": "</s>",
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
+  "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "unk_token": "<unk>",
   "use_default_system_prompt": true
 }