tokenizer_config.json

{
  "unk_token": "[UNK]",
  "sep_token": "[SEP]",
  "pad_token": "[PAD]",
  "cls_token": "[CLS]",
  "mask_token": "[MASK]",
  "do_lower_case": false,
  "do_word_tokenize": true,
  "do_subword_tokenize": true,
  "word_tokenizer_type": "basic",
  "subword_tokenizer_type": "character",
  "never_split": null,
  "mecab_kwargs": null,
  "special_tokens_map_file": null,
  "tokenizer_class": "BertJapaneseTokenizer"
}