Update README.md

README.md

@@ -6,7 +6,7 @@ license: apache-2.0
 
 ### Basic information
 
-This protein language model is an autoregressive transformer model in GPT-style, trained to analyze and predict the mechanical properties of a large number of protein sequences. 
+This protein language model is an autoregressive transformer model in GPT-style, trained to analyze and predict the mechanical properties of a large number of protein sequences. The model has both forward and inverse capabilities. For instance, using generate tasks, the model can design novel proteins that meet one or more mechanical constraints. 
 
 This protein language foundation model was based on the NeoGPT-X architecture and uses rotary positional embeddings (RoPE). It has 16 attention heads, 36 hidden layers and a hidden size of 1024, an intermediate size of 4096 and uses a GeLU activation function.