instruct_v18/tokenizer_config.json

{
  "backend": "tokenizers",
  "bos_token": "<|bos|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": [
    "<|eos|>",
    "<|sep|>",
    "<|mask|>",
    "<|system|>",
    "<|user|>",
    "<|assistant|>",
    "<|tool|>",
    "<|end|>",
    "<|tool_call|>",
    "<|tool_result|>",
    "<|fim_prefix|>",
    "<|fim_suffix|>",
    "<|fim_middle|>",
    "<|image|>",
    "<|audio|>",
    "<|video|>",
    "<|code|>",
    "<|curl|>",
    "<|email|>",
    "<|cite|>",
    "<|think|>",
    "<|im_start|>",
    "<|im_end|>",
    "<|endofprompt|>",
    "<|repo_name|>",
    "<|file_sep|>",
    "<|image_start|>",
    "<|image_end|>",
    "<|image_pad|>"
  ],
  "max_length": 2048,
  "model_max_length": 1000000000000000019884624838656,
  "pad_to_multiple_of": null,
  "pad_token": "<|pad|>",
  "pad_token_type_id": 0,
  "padding_side": "right",
  "stride": 0,
  "tokenizer_class": "TokenizersBackend",
  "truncation_side": "right",
  "truncation_strategy": "longest_first"
}