Add model card with YAML frontmatter and usage instructions

README.md

@@ -42,8 +42,8 @@ This LoRA adapter adds **execution awareness** capabilities to Qwen/Qwen3-4B-Thi
 - **LoRA Alpha**: 128
 - **Training Samples**: 298
 - **Evaluation Samples**: 323
-- **Execution Prediction Accuracy**: 0.0%
-- **Mean State Accuracy**: 0.0%
+- **Execution Prediction Accuracy**: 20.0%
+- **Mean State Accuracy**: 33.3%
 
 ## 🔧 Usage