{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "/data/private/sunsi/dataset/pretrain_model/co-condenser-marco", "special_tokens_map_file": "/bos/tmp0/luyug/outputs/condenser/models/l2-s6-km-L128-e8-lr1e-4-b256/special_tokens_map.json", "tokenizer_file": null, "tokenizer_class": "BertTokenizer", "init_inputs": []}