From a7b515534d739f6ebb66c5fe2595862ad7118edb Mon Sep 17 00:00:00 2001
From: Ren Xuancheng <jklj077@users.noreply.github.com>
Date: Wed, 4 Dec 2024 18:19:25 +0800
Subject: [PATCH] Update awq.md
---
docs/source/quantization/awq.md | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/docs/source/quantization/awq.md b/docs/source/quantization/awq.md
index ac274fe..2d9b7c2 100644
--- a/docs/source/quantization/awq.md
+++ b/docs/source/quantization/awq.md
@@ -111,12 +111,9 @@ print("Chat response:", chat_response)
## Quantize Your Own Model with AutoAWQ
If you want to quantize your own model to AWQ quantized models, we advise you to use AutoAWQ.
-It is suggested installing the latest version of the package by installing from source code:
```bash
-git clone https://github.com/casper-hansen/AutoAWQ.git
-cd AutoAWQ
-pip install -e .
+pip install "autoawq<0.2.7"
```
Suppose you have finetuned a model based on `Qwen2.5-7B`, which is named `Qwen2.5-7B-finetuned`, with your own dataset, e.g., Alpaca.
--
GitLab