Update README.md

README.md

@@ -48,8 +48,10 @@ These are the key hyperparameters used during training:
 
 ## Speed Comparision
 
-We have observed that the distilled models are upto 85% faster than the Base SD1.5 Models. Below is a comparision on an A100 80GB.
+We have observed that the distilled models are upto 80% faster than the Base SD1.5 Models. Below is a comparision on an A100 80GB.
 
 ![graph](./graph.png)
 ![comparision](./comparision1.png)
 
+Below is the code for benchmarking the speeds
+