Update README.md

README.md

@@ -13,13 +13,14 @@ license: mit
 - We were inspired by this [Sakana project](https://sakana.ai/evolutionary-model-merge/)
 
 ## Process
-- 1. two models with the same architecture are needed so fine-tune a model to create a gap between the two of them.
-- 2. merge original one and fine-tuned one
+- you need two models with the same architecture
+- 1. choose one model and fine-tune a model to make a gap between the original one and fine-tuned one. it doesn't matter the evaluation score is higher or lower.
+- 2. merge two of them
 - 3. evaluate the merged model
-- 4. merge again it with original model
+- 4. merge again
 - 5. evaluate again
-- 6. keep going until evaluate avg is higher then original one   
-   
+- 6. keep going until evaluate avg is higher then original one
+
 that's it. simple.
 
 ## Base Model