diff --git a/README.md b/README.md
index dfe4f9c..b864681 100644
--- a/README.md
+++ b/README.md
@@ -38,12 +38,7 @@ This repository contains the AWQ-quantized weights of the instruction-tuned 32B
 
 ## Quickstart
 
-We recommend to use `transformers` v4.43 or later.
-You also need to install the latest version of `AutoAWQ` library, which can be installed by the following command:
-
-```bash
-pip install git+https://github.com/casper-hansen/AutoAWQ.git
-```
+We recommend to use `transformers>=4.43` and `autoawq>=0.2.7.post3`.
 
 Here is the code snippet to run conversational inference with the model: