Update app.py

app.py

@@ -68,11 +68,11 @@ with gr.Blocks() as demo:
         with gr.Column():
             gr.Markdown(f"""
                     ## This demo is an unquantized GPU chatbot of [OpenOrcaxOpenChat-Preview2-13B](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B)
-                    Brought to you by your friends at Alignment Lab AI, Open Chat, and Open Access AI Collective!
+                    Brought to you by your friends at Alignment Lab AI, OpenChat, and Open Access AI Collective!
                     """)
     with gr.Tab("Chatbot"):
         gr.Markdown("# 🐋 OpenOrca x OpenChat - Preview2 - 13B Playground Space! 🐋")
-        chatbot = gr.Chatbot().style(height=800)
+        chatbot = gr.Chatbot().style(height=500)
         with gr.Row():
             message = gr.Textbox(
                 label="What do you want to chat about?",
@@ -85,7 +85,7 @@ with gr.Blocks() as demo:
             stop = gr.Button(value="Stop", variant="secondary").style(full_width=False)
         with gr.Row():
             with gr.Column():
-                max_tokens = gr.Slider(20, 1000, label="Max Tokens", step=20, value=300)
+                max_tokens = gr.Slider(20, 1000, label="Max Tokens", step=20, value=500)
                 temperature = gr.Slider(0.2, 2.0, label="Temperature", step=0.1, value=0.8)
                 top_p = gr.Slider(0.0, 1.0, label="Top P", step=0.05, value=0.95)
                 top_k = gr.Slider(0, 100, label="Top K", step=1, value=40)
@@ -105,4 +105,4 @@ with gr.Blocks() as demo:
         )
         stop.click(fn=None, inputs=None, outputs=None, cancels=[submit_click_event], queue=False)
 
-demo.queue(max_size=48, concurrency_count=16).launch(debug=True, server_name="0.0.0.0", server_port=7860)
+demo.queue(max_size=128, concurrency_count=48).launch(debug=True, server_name="0.0.0.0", server_port=7860)