| { | |
| "added_tokens_decoder": { | |
| "32": { | |
| "content": "[SEP]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "33": { | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "34": { | |
| "content": "[CLS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "35": { | |
| "content": "[MASK]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "tokenizer.RookTokenizer", | |
| null | |
| ] | |
| }, | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "[CLS]", | |
| "mask_token": "[MASK]", | |
| "model_max_length": 78, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "tokenizer_class": "RookTokenizer" | |
| } | |