| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "[CLS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "[SEP]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "4": { | |
| "content": "[MASK]", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [], | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "line-corporation/line-distilbert-base-japanese--distilbert_japanese_tokenizer.DistilBertJapaneseTokenizer", | |
| null | |
| ] | |
| }, | |
| "bos_token": "[CLS]", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": true, | |
| "do_subword_tokenize": true, | |
| "do_word_tokenize": true, | |
| "eos_token": "[SEP]", | |
| "jumanpp_kwargs": null, | |
| "keep_accents": true, | |
| "mask_token": "[MASK]", | |
| "mecab_kwargs": { | |
| "mecab_dic": "unidic_lite" | |
| }, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "never_split": null, | |
| "pad_token": "<pad>", | |
| "remove_space": true, | |
| "sep_token": "[SEP]", | |
| "subword_tokenizer_type": "sentencepiece", | |
| "sudachi_kwargs": null, | |
| "tokenize_chinese_chars": false, | |
| "tokenizer_class": "BertJapaneseTokenizer", | |
| "tokenizer_file": null, | |
| "unk_token": "<unk>", | |
| "word_tokenizer_type": "mecab" | |
| } | |