Update README.md

README.md

@@ -11,7 +11,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # CoVBERT
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+CoVBERT is a protein language model which speaks the language of SARS-CoV-2 spike proteins!
+Enter a sequence with <mask> and let CoVBERT predict the mutation at that position!
+CoVBERT has been trained with 50K spike glycoprotein sequences scraped from [GISAID](https://gisaid.org)
+
+
 It achieves the following results on the evaluation set:
 - Loss: 0.1343