Update README.md

README.md

@@ -7,7 +7,9 @@ An experiment with gradient merges using [the following script](https://github.c
 
 Chronos is a wonderfully verbose model, though it definitely seems to lack in the logic department. Hermes and WizardLM have been merged gradually, primarily in the higher layers (10+) in an attempt to rectify some of this behaviour.
 
-I'd say the end product is about 65% Chronos, with 15% Hermes and 20% Wizard added in gradually increasing amounts. The result feels surprisingly robust, though I'll let you be the final judge of that!
+Below is an illustration attempting to showcase the gradients I used for this specific merge.
+
+![](approximation.png)
 
 This model primarily uses Alpaca formatting, so for optimal model performance, use:
 ```