tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": {},
  "model_max_length": 2048,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "unk_token": "<|endoftext|>",
  "chat_template": "{%- if messages[0].role == 'system' -%}\n  {%- set offset = 1 -%}\n{%- else %}\n  {%- set offset = 0 -%}\n{%- endif -%}\n{{- bos_token -}}\n{%- for message in messages -%}\n  {%- if (message.role == 'user') != (loop.index0 % 2 == offset) -%}\n    {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n  {%- endif -%}\n  {{- '<|im_start|>' + message.role + '\\n' + message.content | trim + '<|im_end|>\\n' -}}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n  {{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}\n"
}