| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<UNK>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<SEP>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "<MASK>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "<CLS>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "4": { | |
| "content": "<PAD>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "<CLS>", | |
| "mask_token": "<MASK>", | |
| "max_length": 512, | |
| "model_max_length": 512, | |
| "pad_token": "<PAD>", | |
| "sep_token": "<SEP>", | |
| "stride": 0, | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<UNK>" | |
| } | |