Update README.md

README.md

@@ -25,7 +25,9 @@ The config looks like this...(detailed version is in the files and versions):
 - [ConvexAI/Metabird-7B](https://huggingface.co/ConvexAI/Metabird-7B) - expert #3
 - [alnrg2arg/test3_sft_16bit](https://huggingface.co/alnrg2arg/test3_sft_16bit) - expert #4
 
-# I just now uploaded it to Open LLM Evaluations, just to see how it will do.
+# It manages to beat Buttercup-4x7B in MMLU, and I personally think it's on-par to it, if not better.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/hQ44cGgs0cSf-sIv8Xk01.png)
 
 # "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)"
 ### (from the MistralAI papers...click the quoted question above to navigate to it directly.)