| { | |
| "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 | |
| }, | |
| "32768": { | |
| "content": "<ent>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32769": { | |
| "content": "<ent2>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<ent>", | |
| "<ent2>", | |
| "<ent>", | |
| "<ent2>", | |
| "<ent>", | |
| "<ent2>", | |
| "<ent>", | |
| "<ent2>" | |
| ], | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "tokenization_ubke_bert_japanese.UbkeBertJapaneseTokenizer", | |
| null | |
| ] | |
| }, | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "do_subword_tokenize": true, | |
| "do_word_tokenize": true, | |
| "entity_mask2_token": "[MASK2]", | |
| "entity_mask_token": "[MASK]", | |
| "entity_pad_token": "[PAD]", | |
| "entity_token_1": "<ent>", | |
| "entity_token_2": "<ent2>", | |
| "entity_unk_token": "[UNK]", | |
| "jumanpp_kwargs": null, | |
| "mask_token": "[MASK]", | |
| "max_entity_length": 32, | |
| "max_mention_length": 30, | |
| "mecab_kwargs": { | |
| "mecab_dic": "unidic_lite" | |
| }, | |
| "model_max_length": 512, | |
| "never_split": null, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "subword_tokenizer_type": "wordpiece", | |
| "sudachi_kwargs": null, | |
| "task": null, | |
| "tokenizer_class": "UbkeBertJapaneseTokenizer", | |
| "unk_token": "[UNK]", | |
| "word_tokenizer_type": "mecab" | |
| } |