| { | |
| "auto_map": {"AutoTokenizer":["ud.BertJapaneseTokenizer","ud.JumanAlbertTokenizerFast"]}, | |
| "bos_token": "[CLS]", | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "eos_token": "[SEP]", | |
| "keep_accents": true, | |
| "mask_token": { | |
| "__type": "AddedToken", | |
| "content": "[MASK]", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "model_max_length": 514, | |
| "pad_token": "[PAD]", | |
| "remove_space": true, | |
| "sep_token": "[SEP]", | |
| "sp_model_kwargs": {}, | |
| "special_tokens_map_file": null, | |
| "subword_tokenizer_type": "sentencepiece", | |
| "tokenizer_class": "JumanAlbertTokenizerFast", | |
| "unk_token": "[UNK]", | |
| "word_tokenizer_type": "jumanpp" | |
| } | |