Update README.md

README.md

@@ -59,7 +59,7 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+The [original paper](https://arxiv.org/pdf/2103.16801.pdf) achieved 98.15% accuracy while this model achieved only 97.35% which is close. However, this is a multilingual model so it has more tokens than the original paper.
 
 ## Intended uses & limitations