Update README.md

README.md

@@ -13,6 +13,8 @@ Here, we introduce TinyLLaVA-Qwen2-0.5B-SigLIP , which is trained by the [TinyLL
 ### Usage
 Execute the following test code:
 ```python
+from tinyllava.eval.run_tiny_llava import eval_model
+
 model_path = 'Zhang199/TinyLLaVA-Qwen2-0.5B-SigLIP'
 prompt = "What are the things I should be cautious about when I visit here?"
 image_file = "https://llava-vl.github.io/static/images/view.jpg"