Update README.md

README.md

@@ -32,8 +32,7 @@ python3 quantize_quark.py \
 ## Deployment
 Quark has its own export format and allows FP8 quantized models to be efficiently deployed using the SGLang backend.
 ## Evaluation
-Quark currently uses perplexity(PPL) as the evaluation metric for accuracy loss before and after quantization.The specific PPL algorithm can be referenced in the quantize_quark.py.
-The quantization evaluation results are conducted in pseudo-quantization mode, which may slightly differ from the actual quantized inference accuracy. These results are provided for reference only.
+
 #### Evaluation scores
 <table>
   <tr>
@@ -45,11 +44,11 @@ The quantization evaluation results are conducted in pseudo-quantization mode, w
    </td>
   </tr>
   <tr>
-   <td>Perplexity-wikitext2
+   <td>gsm8k
    </td>
-   <td>TBD
+   <td>0.821
    </td>
-   <td>TBD
+   <td>0.817
    </td>
   </tr>
 </table>