From 1b71878f7c91375a4d9fb0e43dbc45b01be9e8b7 Mon Sep 17 00:00:00 2001
From: Casper <casperbh.96@gmail.com>
Date: Tue, 11 Jun 2024 09:56:25 +0200
Subject: [PATCH] Update README.md (#497)

---
 README.md | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index e869c5f2..13dca0b7 100644
--- a/README.md
+++ b/README.md
@@ -16,11 +16,11 @@
     </a>
 </p>
 
-<p align="center" style="margin-bottom: 0px; margin-top: 0px;">
-    <a href="https://www.runpod.io/">
-        <img alt="Sponsored by RunPod" src="https://img.shields.io/badge/Sponsored%20by%20RunPod-673AB6">
-    </a>
-</p>
+<div align="center" style="color: white;">
+    <p>Supported by</p>
+    <a href="https://runpod.io/?utm_source=autoAWQ">
+    <img src="https://i.ibb.co/tZPMrq4/Small-Logo.png" alt="RunPod Logo" width="100" border="0">  </a>
+</div>
 
 AutoAWQ is an easy-to-use package for 4-bit quantized models. AutoAWQ speeds up models by 3x and reduces memory requirements by 3x compared to FP16. AutoAWQ implements the Activation-aware Weight Quantization (AWQ) algorithm for quantizing LLMs.  AutoAWQ was created and improved upon from the [original work](https://github.com/mit-han-lab/llm-awq) from MIT.