Update README.md

README.md

@@ -5,8 +5,9 @@ language:
 ---
 An experiment with gradient merges using [the following script](https://github.com/TehVenomm/LM_Transformers_BlockMerge), with [Chronos](https://huggingface.co/elinas/chronos-13b) as its primary model, augmented by [Hermes](https://huggingface.co/NousResearch/Nous-Hermes-13b) and [Wizard-Vicuna Uncensored](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-HF).
 
-Chronos is a wonderfully verbose model, though it definitely lacks 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 60% Chronos, with 20% 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!
+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!
 
 This model primarily uses Alpaca formatting, so for optimal model performance, use:
 ```