Update README.md

README.md

@@ -21,7 +21,8 @@ pipeline_tag: text-generation
 
 <!-- Provide a longer summary of what this model is. -->
 
-I fine-tuned llama-3 8B on an approach similar to Intel's neural chat language model. I have slightly modified the data sources so it is stronger in coding, math, and writing. I use both SFT and DPO.
+I fine-tuned llama-3 8B on an approach similar to Intel's neural chat language model. I have slightly modified the data sources so it is stronger in coding, math, and writing. I use both SFT and DPO-Positive.
+DPO-Positive dramatically improves performance over DPO. 
 
 - **Developed by:** Locutusque
 - **Model type:** Built with Meta Llama 3