updagt

README.md

@@ -55,7 +55,7 @@ The results of the evaluation are as follows:
 Qwen-VL outperforms current SOTA generalist models on multiple VL tasks and has a more comprehensive coverage in terms of capability range.
 
 <p align="center">
-    <img src="assets/radar.png" width="600"/>
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/radar.png" width="600"/>
 <p>
 
 ### Zero-shot Caption & General VQA
@@ -542,7 +542,7 @@ else:
 ```
 
 <p align="center">
-    <img src="assets/demo_highfive.jpeg" width="500"/>
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo_highfive.jpeg" width="500"/>
 <p>
 
 ## FAQ