Update README.md

README.md

@@ -14,6 +14,10 @@ base_model:
 
 ## RpR v3 Changes:
 
+- The best model from ArliAI yet:
+
+  Extreme creativity and out of the box thinking.
+
 - No longer use QwQ-abliterated as base:
 
   v3 is a re-do of v2 but without the problems stemming from starting out with a QwQ-lorablated base. This turned out to not be a good move as it clearly lobotomizes the model more and was even visible from higher training and eval loss values.