Highlight code

This improves the markdown rendering of your code.

README.md

@@ -12,7 +12,7 @@ OpenVLThinker-7B is a vision-language reasoning model designed to handle multimo
 For more details: [Blog](https://yihe-deng.notion.site/openvlthinker), [GitHub](https://github.com/yihedeng9/OpenVLThinker)
 
 ## How to use
-```
+```python
 from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
 import torch
 from qwen_vl_utils import process_vision_info