tokenizer_config.json

{
  "backend": "tokenizers",
  "bos_token": "<|begin_of_text|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|end_of_text|>",
  "is_local": false,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|pad|>",
  "padding_side": "left",
  "tokenizer_class": "TokenizersBackend",
  "chat_template": "{{bos_token}}\n{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"You are a function calling AI model. You are provided with function signature within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.\\n<tools>\\n\" }}\n    {%- for tool in tools %}[{{- tool | tojson }}]{%- endfor %}\n    {{- \"\\n</tools>\\nFor each function call, return a json object with function name and arguments within <tool_call> </tool_call> tags with the following schema:\\n<tool_call>\\n{'arguments': <args-dict>, 'name': <function-name>}\\n</tool_call>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}{% for message in messages %}{%- if message.role != 'system' %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{%- endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
}