Upload tokenizer_config.json

tokenizer_config.json

@@ -8007,10 +8007,11 @@
   "bos_token": "[gMASK]<sop>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "chat_template": "{{ bos_token }}{%- set loop_messages = messages %}\n{%- for message in loop_messages %}\n    {%- set content = '<|' + message['role'] + '|>'+ message['content'] | trim %}\n    {%- if loop.index0 == 0 %}\n        {%- set content = content %}\n    {%- endif %}\n    {%- if not (loop.last and message['role'] == 'assistant') %}\n        {%- set content = content + '<|endoftext|>' %}\n    {%- endif %}\n    {{- content }}\n{%- endfor %}\n{%- if messages[-1]['role'] != 'assistant' %}\n  {{- '<|assistant|>' }}\n{%- endif %}",
   "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<pad>",
   "padding_side": "left",
-  "tokenizer_class": "PreTrainedTokenizer",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"
 }