Update README.md

README.md

@@ -24,6 +24,22 @@ dataset for this model. This results in a DPO dataset composed by triplets < ”
 - **Batch Size:** 8
 - **LR:** 10−7
 
+## Performance
+
+### Safety Performance (Attack Success Ratio)
+
+|                              | Egida (test) ↓ | DELPHI ↓ | Alert-Base ↓ | Alert-Adv ↓ |
+|------------------------------|:--------------:|:--------:|:------------:|:-----------:|
+| Qwen-2.5-7B-Instruct         |     0.471      |  0.138   |    0.544     |    0.080    |
+| Qwen-2.5-7B-Egida-DPO        |     0.322      |  0.118   |    0.410     |    0.045    |
+
+### General Purpose Performance
+
+|                              | OpenLLM Leaderboard (Average) ↑ | MMLU Generative (ROUGE1) ↑ |
+|------------------------------|:---------------------:|:---------------:|
+| Qwen-2.5-7B-Instruct         |         0.488         |      0.331      |
+| Qwen-2.5-7B-Egida-DPO        |         0.488         |      0.296      |
+
 ## Environmental Impact