Update README.md

README.md

@@ -9,7 +9,7 @@ inference: false
 
 ## What is InternVL?
 
-\[[Paper](https://arxiv.org/abs/2312.14238)\]  \[[GitHub](https://github.com/OpenGVLab/InternVL)\]
+\[[Paper](https://arxiv.org/abs/2312.14238)\]  \[[GitHub](https://github.com/OpenGVLab/InternVL)\]   \[[Chat Demo](https://internvl.opengvlab.com/)\]
 
 InternVL scales up the ViT to _**6B parameters**_ and aligns it with LLM.
 
@@ -21,7 +21,7 @@ It is _**the largest open-source vision/vision-language foundation model (14B)**
 
 ## 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.
+Please refer to this [README](https://github.com/OpenGVLab/InternVL/tree/main/internvl_chat_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.