Update README.md

README.md

@@ -41,14 +41,15 @@ The training process included:
 ## Evaluation
 The model was evaluated using the **MathQA test dataset(2985 examples)** with **accuracy** as the primary metric. The following table compares its performance to other models:
 
-| Model                | Accuracy (%)  |
-|----------------------|---------------|
-| Gemma-2-9b (base)    | 24.02       |
-| Mistral-7B-Instruct   | 22.61       |
-| Llama-3.1-8b-Instruct | 27.37      |
-| Llama-3.2-3b-Instruct | 23.48      |
-| Qwen2.5-7B-Instruct  | 38.69         |
-| **mathGemma-2-9b**  | **48.91**    |
+| Model                 | Accuracy (%)  |
+|-----------------------|---------------|
+| Gemma-2-9b (base)     | 24.02         |
+| Mistral-7B-Instruct   | 22.61         |
+| Llama-3.1-8b-Instruct | 27.37         |
+| Llama-3.2-3b-Instruct | 23.48         |
+| Qwen2-Math-7B-Instruct| 33.13	        |
+| Qwen2.5-7B-Instruct   | 38.69         |
+| **mathGemma-2-9b**    | **48.91**     |
 
 
 ## How to Get Started with the Model