Update README.md

README.md

@@ -28,10 +28,7 @@ pinned: false
   }
 </style>
 
-<div align="center">
-  <h1 style="font-size: 2em;">OpenChat </h1>
-    <h1 style="font-size: 1.50em;">Advancing Open-source Language Models with Mixed-Quality Data</h1>
-</div>
+<link href='https://fonts.googleapis.com/css?family=Source+Sans+Pro' rel='stylesheet' type='text/css'>
 
 <p align="center" style="margin-top: 0px;">
       <a>
@@ -55,24 +52,24 @@ pinned: false
   </a>
 </p>
 
+
 <hr>
 
-<p align="center" style="margin-top: 0px; font-size: 1.5em;">
-    <a href="https://huggingface.co/openchat/openchat_3.5" style="text-decoration: none; color: black; background-color: white; border-radius: 0.6em; padding: 0.03em 0.6em; display: inline-block; ">
-      <span style="color: black; font-weight: bold;">OPENCHAT</span>
-      <span style="color: #0056b3; font-weight: bold;">3.5</span>
-    </a>
+<p align="center" style="margin-top: 0px; font-size: 1.5em; background-color: #0056b3; padding: 0.5em; border-radius: 0.5em; color: white">
+    <a href="https://huggingface.co/openchat/openchat_3.5" style="text-decoration: none; color: white">
+      <span style="font-size: 1.8em; ">OpenChat 3.5</span>
       <br>
     <strong>🔥 First <u>7B</u> model that Achieves Comparable Results with <u>ChatGPT</u> (March)! 
     🔥</strong>
   <br>
   <strong>🏆 <u>#1</u> Open-source model on MT-bench scoring 7.81, outperforming <u>70B</u> models 🏆 </strong>
+   </a>
 </p>
 
 
   <div align="center" style="display: flex; justify-content: center; align-items: center;">
-  <img src="https://github.com/imoneoi/openchat/raw/master/assets/openchat.png" style="width: 35%; margin-right: 2%;"> 
-  <img src="https://github.com/imoneoi/openchat/raw/master/assets/openchat_grok.png" style="width: 37%;">
+  <img src="https://github.com/imoneoi/openchat/raw/master/assets/openchat.png" style="width:45%; margin-right: 2%;"> 
+  <img src="https://github.com/imoneoi/openchat/raw/master/assets/openchat_grok.png" style="width: 47%;">
   </div>
 
 - OpenChat is an innovative library of **open-source language models**, fine-tuned with [**C-RLFT**](https://arxiv.org/pdf/2309.11235.pdf) - a strategy inspired by offline reinforcement learning.