tokenizer_config.json

{
  "add_prefix_space": false,
  "audio_bos_token": "<|audio_start|>",
  "audio_eos_token": "<|audio_end|>",
  "audio_token": "<|audio_pad|>",
  "backend": "tokenizers",
  "bos_token": null,
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "errors": "replace",
  "extra_special_tokens": [
    "<|im_start|>",
    "<|im_end|>",
    "<|object_ref_start|>",
    "<|object_ref_end|>",
    "<|box_start|>",
    "<|box_end|>",
    "<|quad_start|>",
    "<|quad_end|>",
    "<|vision_start|>",
    "<|vision_end|>",
    "<|vision_pad|>",
    "<|image_pad|>",
    "<|video_pad|>"
  ],
  "image_token": "<|image_pad|>",
  "is_local": true,
  "model_max_length": 262144,
  "model_specific_special_tokens": {
    "audio_bos_token": "<|audio_start|>",
    "audio_eos_token": "<|audio_end|>",
    "audio_token": "<|audio_pad|>",
    "image_token": "<|image_pad|>",
    "video_token": "<|video_pad|>",
    "vision_bos_token": "<|vision_start|>",
    "vision_eos_token": "<|vision_end|>"
  },
  "pad_token": "<|endoftext|>",
  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
  "split_special_tokens": false,
  "tokenizer_class": "TokenizersBackend",
  "tool_parser_type": "json_tools",
  "unk_token": null,
  "video_token": "<|video_pad|>",
  "vision_bos_token": "<|vision_start|>",
  "vision_eos_token": "<|vision_end|>"
}