Make the app more scalable.

Increase the concurrent limit to shorten the queue. The inference api should be quite scalable.

app.py

@@ -90,5 +90,6 @@ gr.ChatInterface(
     fn=generate,
     chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
     additional_inputs=additional_inputs,
-    title="Mixtral 46.7B"
+    title="Mixtral 46.7B",
+    concurrency_limit=20
 ).launch(show_api=False)