scorer/tokenizer_config.json

{
  "auto_map": {
    "AutoTokenizer": [
      "line-corporation/line-distilbert-base-japanese--distilbert_japanese_tokenizer.DistilBertJapaneseTokenizer",
      null
    ]
  },
  "bos_token": "[CLS]",
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_lower_case": true,
  "do_subword_tokenize": true,
  "do_word_tokenize": true,
  "eos_token": "[SEP]",
  "is_fast": true,
  "jumanpp_kwargs": null,
  "keep_accents": true,
  "mask_token": {
    "__type": "AddedToken",
    "content": "[MASK]",
    "lstrip": true,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "mecab_kwargs": {
    "mecab_dic": "unidic_lite"
  },
  "model_max_length": 1000000000000000019884624838656,
  "never_split": null,
  "pad_token": "<pad>",
  "remove_space": true,
  "sep_token": "[SEP]",
  "subword_tokenizer_type": "sentencepiece",
  "sudachi_kwargs": null,
  "tokenize_chinese_chars": false,
  "tokenizer_class": "DistilBertJapaneseTokenizer",
  "unk_token": "<unk>",
  "word_tokenizer_type": "mecab"
}