Update README.md

README.md

@@ -10,12 +10,12 @@ license: apache-2.0
   <a href="https://infix-ai.com/research/infir2/">🌐 Project Website</a> &nbsp;
 </p>
 
-We performed **Reinforcement Learning (RL)** on the **InfiR2-7B-Instruct-FP8** model using the **dapo-math-17k** and the **FP8 format**, with hyperparameters shown below.
+We performed **Reinforcement Learning (RL)** on the **InfiR2-7B-Instruct-FP8** model using the **dapo-math-17k** and the **FP8 format** (inference), with hyperparameters shown below.
 
 <div align="center">
 
 
-| Parameter | Value |
+| Parameter(stage2) | Value |
 | :---: | :---: |
 | **Batch Size** | 128 |
 | **N Samples Per Prompt** | 16 |
@@ -85,12 +85,19 @@ Below is the performance comparison of **InfiR2-R1-7B-FP8** on reasoning benchma
       <td align="center">39.48</td>
     </tr>
     <tr>
-      <td align="left"><strong>InfiR2-R1-7B-FP8</strong></td>
+      <td align="left"><strong>InfiR2-7B-Instruct-FP8</strong></td>
       <td align="center">40.62</td>
       <td align="center">55.73</td>
       <td align="center">45.33</td>
       <td align="center">40.31</td>
     </tr>
+    <tr>
+      <td align="left"><strong>InfiR2-R1-7B-FP8</strong></td>
+      <td align="center"><strong>53.64</strong></td>
+      <td align="center"><strong>60.62</strong></td>
+      <td align="center"><strong>49.18</strong></td>
+      <td align="center">39.36</td>
+    </tr>
     </tr>
   </tbody>
 </table>