{ "added_tokens_decoder": { "0": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "250001": { "content": "", "lstrip": true, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "250002": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "additional_special_tokens": [ "" ], "bos_token": "", "clean_up_tokenization_spaces": true, "cls_token": "", "do_lower_case": true, "eos_token": "", "mask_token": "", "max_length": 128, "model_max_length": 128, "pad_to_multiple_of": null, "pad_token": "", "pad_token_type_id": 0, "padding": "max_length", "padding_side": "right", "return_tensors": "pt", "sep_token": "", "stride": 0, "strip_accents": null, "tokenize_chinese_chars": true, "tokenizer_class": "BertTokenizer", "truncation": true, "truncation_side": "right", "truncation_strategy": "longest_first", "unk_token": "" }