Upload tokenizer

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "</s>",
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -137,7 +137,7 @@
     "vocab": {
       "<unk>": 0,
       "<s>": 1,
-      "</s>": 2,
+      "<|im_end|>": 2,
       "<0x00>": 3,
       "<0x01>": 4,
       "<0x02>": 5,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:cc460a0129515b7579ec9f63218012601729de4fbd1b5de8d56dc47e8a204a29
+size 493449

tokenizer_config.json

@@ -1,7 +1,6 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -20,7 +19,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -29,14 +28,11 @@
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
-  "model_max_length": 32768,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false