tokenizer_config.json

{
  "add_prefix_space": null,
  "backend": "tokenizers",
  "bos_token": "<｜begin▁of▁sentence｜>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<｜end▁of▁sentence｜>",
  "extra_special_tokens": [
    "<|User|>",
    "<|Assistant|>"
  ],
  "is_local": true,
  "local_files_only": false,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<｜▁pad▁｜>",
  "processor_class": "DeepseekOCRProcessor",
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": null,
  "use_default_system_prompt": false
}