Add description.

app.py

@@ -21,6 +21,7 @@ title_markdown = ("""
   <div>
     <h1 >VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs</h1>
     <h5 style="margin: 0;">If this demo please you, please give us a star ⭐ on Github or 💖 on this space.</h5>
+    <h6 style="margin: 0;">Note that the current demo only supports <b>vision input</b> and <b>single-turn conversation</b>. More features will be available soon.</h6>
   </div>
 </div>