| { | |
| "add_prefix_space": true, | |
| "backend": "tokenizers", | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "mask_token": "<mask>", | |
| "max_length": 512, | |
| "model_max_length": 8192, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "<pad>", | |
| "pad_token_type_id": 0, | |
| "padding_side": "right", | |
| "sep_token": "</s>", | |
| "sp_model_kwargs": {}, | |
| "stride": 0, | |
| "tokenizer_class": "XLMRobertaTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<unk>" | |
| } | |