| { | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "do_subword_tokenize": true, | |
| "do_word_tokenize": true, | |
| "jumanpp_kwargs": null, | |
| "mask_token": "[MASK]", | |
| "mecab_kwargs": { | |
| "mecab_dic": "unidic_lite" | |
| }, | |
| "model_max_length": 512, | |
| "never_split": null, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "subword_tokenizer_type": "wordpiece", | |
| "sudachi_kwargs": null, | |
| "tokenizer_class": "BertJapaneseTokenizer", | |
| "unk_token": "[UNK]", | |
| "word_tokenizer_type": "mecab" | |
| } | |