Update README.md

README.md

@@ -26,6 +26,9 @@ Calyx_7B was trained on these datasets:
 - Himitsui/Lewd-Assistant-v1
 - athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW-v1-SHUFFLED
 
+# Formatting
+Alpaca works best, but Mistral provides good outputs as well.
+
 ---
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="100"/>](https://github.com/unslothai/unsloth)