{ "add_prefix_space": true, "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 }, "3": { "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true }, "51999": { "content": "", "lstrip": true, "normalized": true, "rstrip": false, "single_word": false, "special": true }, "52000": { "content": "[CLS]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "52001": { "content": "[SEP]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false } }, "bos_token": "", "clean_up_tokenization_spaces": true, "cls_token": "", "eos_token": "", "errors": "replace", "mask_token": "", "max_len": 512, "model_max_length": 512, "pad_token": "", "sep_token": "", "tokenizer_class": "RobertaTokenizer", "trim_offsets": true, "unk_token": "" }