| { | |
| "bos_token": "[CLS]", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": true, | |
| "eos_token": "[SEP]", | |
| "keep_accents": false, | |
| "mask_token": { | |
| "__type": "AddedToken", | |
| "content": "[MASK]", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "max_length": 100, | |
| "model_max_length": 512, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "<pad>", | |
| "pad_token_type_id": 0, | |
| "padding_side": "right", | |
| "remove_space": true, | |
| "sep_token": "[SEP]", | |
| "stride": 0, | |
| "tokenizer_class": "AlbertTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<unk>" | |
| } | |