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",
  "image_token": "<|image_pad|>",
  "is_local": false,
  "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|>",
  "padding_side": "right",
  "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",
  "unk_token": null,
  "video_token": "<|video_pad|>",
  "vision_bos_token": "<|vision_start|>",
  "vision_eos_token": "<|vision_end|>",
  "added_tokens_decoder": {
    "248044": {
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248045": {
      "content": "<|im_start|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248046": {
      "content": "<|im_end|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248047": {
      "content": "<|object_ref_start|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248048": {
      "content": "<|object_ref_end|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248049": {
      "content": "<|box_start|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248050": {
      "content": "<|box_end|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248051": {
      "content": "<|quad_start|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248052": {
      "content": "<|quad_end|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248053": {
      "content": "<|vision_start|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248054": {
      "content": "<|vision_end|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248055": {
      "content": "<|vision_pad|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248056": {
      "content": "<|image_pad|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248057": {
      "content": "<|video_pad|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248058": {
      "content": "<tool_call>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248059": {
      "content": "</tool_call>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248060": {
      "content": "<|fim_prefix|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248061": {
      "content": "<|fim_middle|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248062": {
      "content": "<|fim_suffix|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248063": {
      "content": "<|fim_pad|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248064": {
      "content": "<|repo_name|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248065": {
      "content": "<|file_sep|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248066": {
      "content": "<tool_response>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248067": {
      "content": "</tool_response>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248068": {
      "content": "<think>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248069": {
      "content": "</think>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    "248070": {
      "content": "<|audio_start|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248071": {
      "content": "<|audio_end|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248072": {
      "content": "<tts_pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248073": {
      "content": "<tts_text_bos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248074": {
      "content": "<tts_text_eod>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248075": {
      "content": "<tts_text_bos_single>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "248076": {
      "content": "<|audio_pad|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  }
}