trans-encoder-bi-simcse-bert-large / tokenizer_config.json
fl399's picture
Update from fl418
d1ae5d2
{"do_lower_case": true, "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": "princeton-nlp/unsup-simcse-bert-large-uncased", "special_tokens_map_file": "/home/ubuntu/.cache/huggingface/transformers/9815e6a54fad15bb2fcff74f877cde75e46d6798b672f62366e22d80a373d718.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}