| { | |
| "bos_token": "<s>", | |
| "eos_token": "</s>", | |
| "unk_token": "<unk>", | |
| "sep_token": "</s>", | |
| "cls_token": "<s>", | |
| "pad_token": "<pad>", | |
| "mask_token": { | |
| "content": "<mask>", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": false, | |
| "normalized": true, | |
| "__type": "AddedToken" | |
| }, | |
| "sp_model_kwargs": {}, | |
| "do_lower_case": false, | |
| "do_zenkaku": true, | |
| "do_word_tokenize": true, | |
| "do_subword_tokenize": true, | |
| "word_tokenizer_type": "mecab", | |
| "subword_tokenizer_type": "bpe", | |
| "never_split": null, | |
| "mecab_kwargs": { | |
| "mecab_dic": "unidic_lite" | |
| }, | |
| "special_tokens_map_file": null, | |
| "tokenizer_file": null, | |
| "tokenizer_class": "RobertaJapaneseTokenizer" | |
| } | |