SentMAE_BEIR / tokenizer_config.json
SamuelYang's picture
Upload tokenizer_config.json
27ed9c8
raw
history blame
553 Bytes
{"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": "/ads-nfs/t-shxiao/pretrain_retriever/saved_models/alltokensv2_layer1_encoder015_decoder05/", "special_tokens_map_file": "/ads-nfs/t-shxiao/pretrain_retriever/saved_models/alltokensv2_layer1_encoder015_decoder05/special_tokens_map.json", "tokenizer_class": "BertTokenizer"}