Update README.md

README.md

@@ -5,4 +5,7 @@ language:
 - en
 ---
 
-This is just temporary while I figure out how to make my model play nice with HuggingFace
+This model uses two BERT models fine-tuned on a contrastive learning objective.
+One is responsable for short queries, and the other for longer documents that contain the answer to the query.
+After encoding many documents, one may perform a nearest neighbor search with the query encoding, to fetch
+the most relevant document.