| { | |
| "add_prefix_space": true, | |
| "additional_special_tokens": [ | |
| "--NME--", | |
| "[R-0]", | |
| "[R-1]", | |
| "[R-2]", | |
| "[R-3]", | |
| "[R-4]", | |
| "[R-5]", | |
| "[R-6]", | |
| "[R-7]", | |
| "[R-8]", | |
| "[R-9]", | |
| "[R-10]", | |
| "[R-11]", | |
| "[R-12]", | |
| "[R-13]", | |
| "[R-14]", | |
| "[R-15]", | |
| "[R-16]", | |
| "[R-17]", | |
| "[R-18]", | |
| "[R-19]", | |
| "[R-20]", | |
| "[R-21]", | |
| "[R-22]", | |
| "[R-23]" | |
| ], | |
| "bos_token": "[CLS]", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "eos_token": "[SEP]", | |
| "mask_token": "[MASK]", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "sp_model_kwargs": {}, | |
| "split_by_punct": false, | |
| "tokenizer_class": "DebertaV2Tokenizer", | |
| "unk_token": "[UNK]", | |
| "vocab_type": "spm" | |
| } | |