初始化项目,由ModelHub XC社区提供模型

Model: BAAI/bge-base-zh-v1.5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-14 13:09:40 +08:00
commit 145c8ee4eb
13 changed files with 42962 additions and 0 deletions

15
tokenizer_config.json Normal file
View File

@@ -0,0 +1,15 @@
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}