初始化项目,由ModelHub XC社区提供模型

Model: BAAI/bge-m3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-23 12:26:20 +08:00
commit e88bf1e540
30 changed files with 635 additions and 0 deletions

20
tokenizer_config.json Normal file
View File

@@ -0,0 +1,20 @@
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 8192,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}