Update README.md

README.md

@@ -15,7 +15,7 @@ tags:
 
 # Fireball-12B-V1.0
 This model is super fine-tune to provide better coding and better response(from first fine-tune) than Llama-3.1-8B and Google Gemma 2 9B. 
-Further fine tuned with ORPO method with dataset.  DPO fine-tuned again with much higher quality tuning. 
+Further fine tuned with ORPO method with dataset.  ORPO fine-tuned again with much higher quality tuning. 
 - reciperesearch/dolphin-sft-v0.1-preference
 
 # Benchmark