| { | |
| "bos_token": "[CLS]", | |
| "cls_token": "[CLS]", | |
| "eos_token": "[SEP]", | |
| "mask_token": "[MASK]", | |
| "model_max_length": 2048, | |
| "name_or_path": "tokenizers/tok-sample.txt-wordpiece-32000-pretok.json", | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "unk_token": "[UNK]" | |
| } | |