Update README.md

README.md

@@ -4,6 +4,7 @@ pipeline_tag: visual-question-answering
 ---
 # 😈Imp
 
+\[Technical report (coming soon)\]  [[Demo](https://xmbot,net/imp/)\]  [[Github](https://github.com/MILVLG/imp)\]
 
 The Imp project aims to provide a family of  a strong multimodal `small` language models (MSLMs). Our `imp-v1-3b` is a strong MSLM with only **3B** parameters, which is build upon a small yet powerful SLM [Phi-2 ](https://huggingface.co/microsoft/phi-2)(2.7B) and a powerful visual encoder [SigLIP ](https://huggingface.co/google/siglip-so400m-patch14-384)(0.4B), and trained on the [LLaVA-v1.5](https://github.com/haotian-liu/LLaVA) training set.  
 
@@ -14,7 +15,7 @@ We release our model weights and provide an example below to run our model . Det
 
 ## How to use
 
-You can use the following code for model inference. We minimize the required dependency libraries that only the `transformers` and `torch` packages are used. The format of text instructions is similar to [LLaVA](https://github.com/haotian-liu/LLaVA).
+You can use the following code for model inference. We minimize the required dependency libraries that only the `transformers` and `torch` packages are used. The latest version of `transformers` is ok but we recommand v4.3.0. The format of text instructions is similar to [LLaVA](https://github.com/haotian-liu/LLaVA).
 
 ```Python
 import torch