| { | |
| "add_prefix_space": true, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "65": { | |
| "content": "[CLS]", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "66": { | |
| "content": "[SEP]", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "67": { | |
| "content": "[MASK]", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "100": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50358": { | |
| "content": "<SEP2>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50359": { | |
| "content": "<EOS>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [], | |
| "bos_token": "</s>", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "eos_token": "<EOS>", | |
| "mask_token": "[MASK]", | |
| "model_max_length": 4096, | |
| "pad_token": "<pad>", | |
| "sep_token": "<SEP2>", | |
| "sp_model_kwargs": {}, | |
| "tokenizer_class": "BigBirdTokenizer", | |
| "unk_token": "<unk>" | |
| } | |