Update README.md

README.md

@@ -191,9 +191,14 @@ Average Score Comparison between OpenHermes-1 Llama-2 13B and OpenHermes-2 Mistr
 |Average Total  |            47.17|                    51.42|                    52.38|               +5.21|               +0.96|
 ```
 
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ADy7p-xIG8qGlC5ZliqpW.png)
+
 **HumanEval:**
+On code tasks, I first set out to make a hermes-2 coder, but found that it can have generalist improvements to the model, so I settled for slightly less code capabilities, for maximum generalist ones. That said, code capabilities had a decent jump alongside the overall capabilities of the model:
 HumanEval: 50.7% @ Pass1
 
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/IeeZnGmEyK73ejq0fKEms.png)
+
 # Prompt Format
 
 OpenHermes 2.5 now uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.