Update README.md

README.md

@@ -7,7 +7,8 @@ license: cc-by-nc-sa-4.0
 # Frankenstein-MoE
 
 ### Method
-To initialize the gate projection weight of the MoE layer, the H6 trainset was sampled and used. We sampled 400 and selected the final 30 with low PPL.
+To initialize the gate projection weight of the MoE layer, the H6 trainset was sampled and used. We sampled 400 and selected the final 30 with low PPL.  
+
 trufulqa used gpt4 to generate data.
 
 ### Evals