Update README.md

README.md

@@ -26,6 +26,8 @@ This model was fine-tuned using LoRa on 1 T4 GPU. The model was trained for 10,0
 ## Evaluation results
 
 We evaluate our models on the MultiPle-E bencchmark. The model achieves 8.9 Pass@10 Rate.
+![final_pass_at_10](https://raw.githubusercontent.com/ammarnasr/LLM-for-code-intelligence/main/figs/final_pass_at_10.png)
+
 
 
 ## Intended Use and Limitations