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": "<|im_start|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "errors": "replace",
  "image_end_token": "</image>",
  "image_id_end_token": "</image_id>",
  "image_id_start_token": "<image_id>",
  "image_start_token": "<image>",
  "image_token": "<|image_pad|>",
  "is_local": false,
  "local_files_only": false,
  "model_max_length": 262144,
  "model_specific_special_tokens": {
    "audio_bos_token": "<|audio_start|>",
    "audio_eos_token": "<|audio_end|>",
    "audio_token": "<|audio_pad|>",
    "image_end_token": "</image>",
    "image_id_end_token": "</image_id>",
    "image_id_start_token": "<image_id>",
    "image_start_token": "<image>",
    "image_token": "<|image_pad|>",
    "slice_end_token": "</slice>",
    "slice_start_token": "<slice>",
    "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+",
  "processor_class": "MiniCPMV4_6Processor",
  "slice_end_token": "</slice>",
  "slice_start_token": "<slice>",
  "split_special_tokens": false,
  "tokenizer_class": "TokenizersBackend",
  "unk_token": "<unk>",
  "video_token": "<|video_pad|>",
  "vision_bos_token": "<|vision_start|>",
  "vision_eos_token": "<|vision_end|>"
}