| { | |
| "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": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [], | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "do_nfkc": false, | |
| "do_subword_tokenize": true, | |
| "do_word_tokenize": true, | |
| "mask_token": "[MASK]", | |
| "model_max_length": 512, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "subword_tokenizer_type": "wordpiece", | |
| "sudachipy_kwargs": { | |
| "dict_type": "core", | |
| "split_mode": "A" | |
| }, | |
| "tokenizer_class": "ElectraSudachipyTokenizer", | |
| "tokenizer_file": null, | |
| "unk_token": "[UNK]", | |
| "word_form_type": "dictionary_and_surface", | |
| "word_tokenizer_type": "sudachipy" | |
| } | |