初始化项目,由ModelHub XC社区提供模型
Model: intfloat/multilingual-e5-small Source: Original Platform
This commit is contained in:
20
tokenizer_config.json
Normal file
20
tokenizer_config.json
Normal 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": 512,
|
||||
"pad_token": "<pad>",
|
||||
"sep_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "XLMRobertaTokenizer",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in New Issue
Block a user