| { | |
| "do_lower_case": false, | |
| "do_nfkc": true, | |
| "do_word_tokenize": true, | |
| "do_subword_tokenize": true, | |
| "word_tokenizer_type": "sudachi", | |
| "subword_tokenizer_type": "wordpiece", | |
| "unk_token": "[UNK]", | |
| "sep_token": "[SEP]", | |
| "pad_token": "[PAD]", | |
| "cls_token": "[CLS]", | |
| "mask_token": "[MASK]", | |
| "sudachi_kwargs": { | |
| "sudachi_split_mode": "C", | |
| "sudachi_dict_type": "core" | |
| }, | |
| "model_max_length": 512, | |
| "tokenizer_class": "BertJapaneseTokenizer" | |
| } |