tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "71013": {
      "content": "|ENDOFTEXT|",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "262144": {
      "content": "|ENDOFIMAGE|",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "262145": {
      "content": "|IMAGE|",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "|ENDOFIMAGE|",
    "|IMAGE|"
  ],
  "bos_token": "|ENDOFTEXT|",
  "clean_up_tokenization_spaces": false,
  "eos_token": "|ENDOFTEXT|",
  "legacy": true,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<unk>",
  "processor_class": "MFuyuProcessor",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": true
}