intfloat commited on
Commit
f6947f9
·
1 Parent(s): 35d4ac7

update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -83,16 +83,16 @@ Contributors: [michaelfeil](https://huggingface.co/michaelfeil)
83
 
84
  ## FAQ
85
 
86
- **1. Do I need to add the prefix `query: ` and `passage: ` to input texts?**
87
 
88
  Yes, this is how the model is trained, otherwise you will see a performance degradation.
89
 
90
  Here are some rules of thumb:
91
- - Use `query: ` and `passage: ` correspondingly for asymmetric tasks such as passage retrieval in open QA, ad-hoc information retrieval.
92
 
93
- - Use `query: ` prefix for symmetric tasks such as semantic similarity, paraphrase retrieval.
94
 
95
- - Use `query: ` prefix if you want to use embeddings as features, such as linear probing classification, clustering.
96
 
97
  **2. Why are my reproduced results slightly different from reported in the model card?**
98
 
 
83
 
84
  ## FAQ
85
 
86
+ **1. Do I need to add the prefix "query: " and "passage: " to input texts?**
87
 
88
  Yes, this is how the model is trained, otherwise you will see a performance degradation.
89
 
90
  Here are some rules of thumb:
91
+ - Use "query: " and "passage: " correspondingly for asymmetric tasks such as passage retrieval in open QA, ad-hoc information retrieval.
92
 
93
+ - Use "query: " prefix for symmetric tasks such as semantic similarity, paraphrase retrieval.
94
 
95
+ - Use "query: " prefix if you want to use embeddings as features, such as linear probing classification, clustering.
96
 
97
  **2. Why are my reproduced results slightly different from reported in the model card?**
98