Add top-of-page benchmark figure

README.md

@@ -96,6 +96,8 @@ It supports Chinese-English image-text retrieval, zero-shot image classification
 
 This is the smallest published M2-Encoder variant and is the best starting point for CPU demos, Spaces, and lightweight retrieval services.
 
+![Benchmark overview](https://raw.githubusercontent.com/alipay/Ant-Multi-Modal-Framework/main/prj/M2_Encoder/pics/effect.png)
+
 ## Links
 
 - Paper: https://arxiv.org/abs/2401.15896