{"added_tokens_decoder": {"13970": {"content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "29051": {"content": "[UNK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "4889": {"content": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "2578": {"content": "[SEP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "10737": {"content": "[MASK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}}, "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_basic_tokenize": true, "do_lower_case": true, "extra_special_tokens": {}, "mask_token": "[MASK]", "model_max_length": 512, "never_split": null, "pad_token": "[PAD]", "sep_token": "[SEP]", "strip_accents": null, "tokenize_chinese_chars": true, "tokenizer_class": "DistilBertTokenizer", "unk_token": "[UNK]"}