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 larger M2-Encoder variant with a wider backbone and 1024-dimensional embeddings, intended for better retrieval and zero-shot classification quality.
 
+![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