Update README.md

README.md

@@ -5,8 +5,8 @@ license: mit
 # ESM-2 for Predicting Binding Sites
 
 This is the 650M parameter version of ESM-2, finetuned with QLoRA to predict binding sites of proteins based on single sequences alone. 
-No multiple sequence alignement is required. The embeddings from this model can also be used in structural models. The model is trained on 
-approximately 12M protein sequences, with an 80/20 train/test split. 
+No multiple sequence alignment or structure is required. The embeddings from this model can also be used in structural models. The model is trained on 
+approximately 12M protein sequences from UniProt, with an 80/20 train/test split. 
 
 ## Using the Model