{ "added_tokens_decoder": { "3": { "content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "4": { "content": "[UNK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "5": { "content": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "6": { "content": "[SEP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "7": { "content": "[MASK]", "lstrip": true, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "bos_token": "[CLS]", "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_lower_case": true, "eos_token": "[SEP]", "keep_acccents": false, "keep_accent": false, "keep_accents": true, "mask_token": "[MASK]", "max_len": 128, "max_length": 128, "model_max_length": 128, "pad_to_multiple_of": null, "pad_token": "[PAD]", "pad_token_type_id": 0, "padding_side": "right", "remove_space": true, "sep_token": "[SEP]", "sp_model_kwargs": {}, "stride": 0, "tokenizer_class": "AlbertTokenizer", "truncation_side": "right", "truncation_strategy": "longest_first", "unk_token": "[UNK]" }