tokenizer_config.json

{
  "add_prefix_space": false,
  "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_break_token": "<|vision_pad|>",
  "image_end_token": "<|vision_end|>",
  "image_token": "<|image_pad|>",
  "is_local": false,
  "max_length": null,
  "model_max_length": 131072,
  "model_specific_special_tokens": {},
  "pad_to_multiple_of": null,
  "pad_token": "<|endoftext|>",
  "pad_token_type_id": 0,
  "padding_side": "left",
  "processor_class": "LightOnOcrProcessor",
  "split_special_tokens": false,
  "tokenizer_class": "TokenizersBackend",
  "unk_token": null
}