| { | |
| "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, | |
| "name_or_path": "megagonlabs/transformers-ud-japanese-electra-base-discriminator", | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "special_tokens_map_file": "/root/.cache/huggingface/hub/models--megagonlabs--transformers-ud-japanese-electra-base-discriminator/snapshots/96a3711b754c2caf0d1e22b30cbb893a37fa46c2/special_tokens_map.json", | |
| "subword_tokenizer_type": "wordpiece", | |
| "sudachipy_kwargs": { | |
| "dict_type": "core", | |
| "split_mode": "A" | |
| }, | |
| "tokenizer_class": "ElectraSudachipyTokenizer", | |
| "unk_token": "[UNK]", | |
| "word_form_type": "dictionary_and_surface", | |
| "word_tokenizer_type": "sudachipy" | |
| } | |