{ "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_basic_tokenize": true, "do_lower_case": false, "mask_token": "[MASK]", "max_len": 128, "model_max_length": 128, "never_split": null, "pad_token": "[PAD]", "sep_token": "[SEP]", "strip_accents": false, "tokenize_chinese_chars": true, "tokenizer_class": "DistilBertTokenizer", "unk_token": "[UNK]" }