{ "cls_token": "[CLS]", "do_basic_tokenize": true, "do_lower_case": false, "mask_token": "[MASK]", "max_len": 128, "name_or_path": "../../data11/model/sbert/sbert-mbertV2.0-distil", "never_split": null, "pad_token": "[PAD]", "sep_token": "[SEP]", "special_tokens_map_file": "../tokenizer_sample/moco-vocab/moco-corpus-kowiki202206-42000/special_tokens_map.json", "strip_accents": false, "tokenize_chinese_chars": true, "tokenizer_class": "BertTokenizer", "unk_token": "[UNK]" }