diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5bdf272 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"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, "name_or_path": "hfl/chinese-macbert-base", "tokenizer_class": "BertTokenizer"}