| { | |
| "backend": "tokenizers", | |
| "bos_token": "[CLS]", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "eos_token": "[SEP]", | |
| "extra_special_tokens": [ | |
| "[SEP_STRUCT]", | |
| "[SEP_TEXT]", | |
| "[P]", | |
| "[C]", | |
| "[E]", | |
| "[R]", | |
| "[L]", | |
| "[EXAMPLE]", | |
| "[OUTPUT]", | |
| "[DESCRIPTION]" | |
| ], | |
| "is_local": false, | |
| "mask_token": "[MASK]", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "sp_model_kwargs": {}, | |
| "split_by_punct": false, | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": "[UNK]", | |
| "vocab_type": "spm" | |
| } | |