{ "added_tokens_decoder": { "0": { "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "", "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": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true } }, "attention_type": "block_sparse", "block_size": 2, "bos_token": "", "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "eos_token": "", "mask_token": "[MASK]", "max_length": 4096, "model_max_length": 4096, "pad_to_multiple_of": null, "pad_token": "", "pad_token_type_id": 0, "padding_side": "right", "sep_token": "[SEP]", "sp_model_kwargs": {}, "tokenizer_class": "BigBirdTokenizer", "unk_token": "" }