Update README.md

README.md

@@ -40,10 +40,10 @@ We provide dequantized model weights in bfloat16 to run DeepSeek-R1 on Metax GPU
 
 # Bundle Download
 
-|   |  FlagRelease version | 
-|----------|----------|
-| Basic Image   | docker pull flagrelease-registry.cn-beijing.cr.aliyuncs.com/flagrelease/flagrelease:deepseek-flagos-metax   | 
-| Model   | https://www.modelscope.cn/models/FlagRelease/DeepSeek-R1-FlagOS-Metax-FP16   | 
+|             | Usage                                                  | Metax                                                                                                       |
+| ----------- | ------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------- |
+| Basic Image | basic software environment that supports model running | `docker pull flagrelease-registry.cn-beijing.cr.aliyuncs.com/flagrelease/flagrelease:deepseek-flagos-metax` |
+| Model       | model weight and configuration files                   | https://www.modelscope.cn/models/FlagRelease/DeepSeek-R1-FlagOS-Metax-FP16                                  |
 
 # Evaluation Results