Update README.md

README.md

@@ -94,10 +94,14 @@ VideoChat-Flash-7B is constructed upon UMT-L (300M) and Qwen2-7B, employing only
 ## 🚀 How to use the model
 
 
-### Generation
-
-We provide the simple generation process for using our model. For more details, you could refer to [Github](https://github.com/LLaVA-VL/LLaVA-NeXT).
 
+We provide the simple conversation process for using our model. You need to install [flash attention2](https://github.com/Dao-AILab/flash-attention) to use our visual encoder.
+```
+pip install transformers==4.39.2
+pip install timm
+pip install flash-attn --no-build-isolation
+```
+Then you could use our model:
 ```python
 from transformers import AutoModel, AutoTokenizer