Update README.md

README.md

@@ -56,6 +56,12 @@ The primary intended users of the model are researchers and hobbyists in compute
 ## Evaluation dataset
 A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.
 
+## How to Run?
+
+Please refer to this [README](https://github.com/OpenGVLab/InternVL/tree/main/llava#internvl-for-multimodal-dialogue-using-llava) to run this model.
+
+Note: We have retained the original documentation of LLaVA 1.5 as a more detailed manual. In most cases, you will only need to refer to the new documentation that we have added.
+
 ## Acknowledgement
 
 This model card is adapted from [LLaVA's model card](https://huggingface.co/liuhaotian/llava-v1.5-13b). Thanks for their awesome work!