Update README.md

README.md

@@ -41,7 +41,7 @@ As a masked language model this tool can be used to predict expected mutations u
 
 ## Training Data
 
-The dataset damlab/HIV-FLT was used to refine the original rostlab/Prot-bert-bfd. This dataset contains 1790 full HIV genomes from across the globe. When translated, these genomes contain approximately 3.9 million amino-acid tokens.
+The dataset damlab/HIV_FLT was used to refine the original rostlab/Prot-bert-bfd. This dataset contains 1790 full HIV genomes from across the globe. When translated, these genomes contain approximately 3.9 million amino-acid tokens.
 
 ## Training Procedure