Update to use latest delta weights

Adapt to new changes. related prs:
https://github.com/lm-sys/FastChat/pull/189
https://github.com/lm-sys/FastChat/pull/167

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/ubuntu/llama-13b-hf",
+  "_name_or_path": "/root/llama-13b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066db2c1b346e034de827bc4d47e2ce580e1e4e0b79c8a1184b5bb4c29f3e2d0
-size 9948735223
+oid sha256:0bac14d265d543d2ec08047c274bfdf5eda35140cf20d3c70dd31c02dbca62e6
+size 9948738670

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e60dfcb3c3abb2c146412763cccdc8357f47f7f53704866819d74d775cbf91
-size 9904161599
+oid sha256:668c7ef449e4aafd76cb4f63fc3b0bcbfa165bb004352ede1b727eb0d59aa8ef
+size 9904165024

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc35c8d0827911e51b61743d77aac22f017468c0f33576286e4231e89f110e24
-size 6506671316
+oid sha256:53a19ed5c724554b5315902b26519708e166d57827d559fb1f1cec1c57db3da9
+size 6506673929

special_tokens_map.json

@@ -1,6 +1,23 @@
 {
-  "bos_token": "</s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "</s>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,10 +1,34 @@
 {
-  "bos_token": "",
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "clean_up_tokenization_spaces": false,
-  "eos_token": "",
-  "model_max_length": 2048,
-  "padding_side": "right",
-  "special_tokens_map_file": "/home/gcpuser/hf-output/llama-13b/special_tokens_map.json",
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/vicuna-13b-delta-v0/special_tokens_map.json",
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": ""
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }