tokenizer_config.json

{
    "do_lower_case": false,
    "remove_space": true,
    "keep_accents": true,
    "bos_token": "[CLS]",
    "eos_token": "[SEP]",
    "unk_token": "[UNK]",
    "sep_token": "[SEP]",
    "pad_token": "[PAD]",
    "cls_token": "[CLS]",
    "mask_token": {
        "content": "[MASK]",
        "single_word": false,
        "lstrip": true,
        "rstrip": false,
        "normalized": true,
        "__type": "AddedToken"
    },
    "sp_model_kwargs": {},
    "special_tokens_map_file": null,
    "tokenizer_class": "BertJapaneseTokenizer",
    "word_tokenizer_type": "jumanpp",
    "subword_tokenizer_type": "sentencepiece",
    "jumanpp_kwargs": {}
}