Update tokenizer_config.json

tokenizer_config.json

@@ -152,30 +152,31 @@
  "rstrip": false,
  "single_word": false,
  "special": true
- },
- "49152": {
- "content": "<|im_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "49153": {
- "content": "<|im_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
  }
  },
  "additional_special_tokens": [
- "<|im_start|>",
- "<|im_end|>"
+ "<|endoftext|>",
+ "<fim_prefix>",
+ "<fim_middle>",
+ "<fim_suffix>",
+ "<fim_pad>",
+ "<filename>",
+ "<gh_stars>",
+ "<issue_start>",
+ "<issue_comment>",
+ "<issue_closed>",
+ "<jupyter_start>",
+ "<jupyter_text>",
+ "<jupyter_code>",
+ "<jupyter_output>",
+ "<empty_output>",
+ "<commit_before>",
+ "<commit_msg>",
+ "<commit_after>",
+ "<reponame>"
  ],
  "bos_token": "<|endoftext|>",
- "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'Question:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'system' %}\n{{ 'System:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Answer:\n' + message['content'] + '\n\n' }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Answer:\n' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "model_max_length": 9223372036854775807,
@@ -184,5 +185,4 @@
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>",
  "vocab_size": 49152
-}
-
+}