Tokenizers

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e5daf1e619597fd56ff036925ea189916417c665d5bdd61b80199cf8d4e6d2
-size 17078029
+oid sha256:94298edb1189fa83fdb219ce9ae8a4e3e257aa07c86309f5fffae782fbeefffe
+size 17078146

tokenizer_config.json

@@ -8008,14 +8008,14 @@
     "<|im_start|>"
   ],
   "bos_token": "<s>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
+  "fix_mistral_regex": true,
   "legacy": true,
   "model_max_length": 131072,
   "pad_token": "<pad>",
-  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_class": "LlamaTokenizerFast",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }