Update README.md

README.md

@@ -18,6 +18,6 @@ The goal was to reduce archaic language and purple prose in a completely uncenso
 
 ### Method
 
-[ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 2x A100 for 10 epochs.
+[ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 8x A40 for 10 epochs.
 
 For this version, beta was increased to 0.5 and learning rate was increased to 8e-6 (the original in v1).