Update README.md

README.md

@@ -2699,6 +2699,14 @@ Here are some rules of thumb:
 
 Different versions of `transformers` and `pytorch` could cause negligible but non-zero performance differences.
 
+**3. Why does the cosine similarity scores distribute around 0.7 to 1.0?**
+
+This is a known and expected behavior as we use a low temperature 0.01 for InfoNCE contrastive loss. 
+
+For text embedding tasks like text retrieval or semantic similarity, 
+what matters is the relative order of the scores instead of the absolute values, 
+so this should not be an issue.
+
 ## Citation
 
 If you find our paper or models helpful, please consider cite as follows: