Update app.py

app.py

@@ -48,29 +48,49 @@ def chat(history, system_message, max_tokens, temperature, top_p, top_k, repetit
             history[-1][1] += answer
             yield history, history, ""
 
-with gr.Blocks() as demo:
+with gr.Blocks(css=CSS) as demo:
     with gr.Row():
         with gr.Column():
-            gr.Markdown(f"""## Mistral-7B-OpenOrca Playground Space!""")
+            gr.Markdown(f"""
+                    ## This demo is an unquantized GPU chatbot of [Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
+                    Brought to you by your friends at Alignment Lab AI, OpenChat, and Open Access AI Collective!
+                    """)
     with gr.Row():
+        gr.Markdown("# 🐋 Mistral-7B-OpenOrca Playground Space! 🐋")
+    with gr.Row():
+        #chatbot = gr.Chatbot().style(height=500)
         chatbot = gr.Chatbot(elem_id="chatbot")
     with gr.Row():
-        message = gr.Textbox(label="What do you want to chat about?", placeholder="Ask me anything.", lines=3)
+        message = gr.Textbox(
+            label="What do you want to chat about?",
+            placeholder="Ask me anything.",
+            lines=3,
+        )
     with gr.Row():
-        submit = gr.Button(value="Send message", variant="secondary")
-        clear = gr.Button(value="New topic", variant="secondary")
+        submit = gr.Button(value="Send message", variant="secondary").style(full_width=True)
+        clear = gr.Button(value="New topic", variant="secondary").style(full_width=False)
+        stop = gr.Button(value="Stop", variant="secondary").style(full_width=False)
     with gr.Accordion("Show Model Parameters", open=False):
         with gr.Row():
             with gr.Column():
-                max_tokens = gr.Slider(20, 2500, step=20, value=500)
-                temperature = gr.Slider(0.0, 2.0, step=0.1, value=0.4)
-                top_p = gr.Slider(0.0, 1.0, step=0.05, value=0.95)
-                top_k = gr.Slider(1, 100, step=1, value=40)
-                repetition_penalty = gr.Slider(1.0, 2.0, step=0.1, value=1.1)
-        system_msg = gr.Textbox(BASE_SYSTEM_MESSAGE, lines=5)
+                max_tokens = gr.Slider(20, 2500, label="Max Tokens", step=20, value=500)
+                temperature = gr.Slider(0.0, 2.0, label="Temperature", step=0.1, value=0.4)
+                top_p = gr.Slider(0.0, 1.0, label="Top P", step=0.05, value=0.95)
+                top_k = gr.Slider(1, 100, label="Top K", step=1, value=40)
+                repetition_penalty = gr.Slider(1.0, 2.0, label="Repetition Penalty", step=0.1, value=1.1)
+
+        system_msg = gr.Textbox(
+            start_message, label="System Message", interactive=True, visible=True, placeholder="System prompt. Provide instructions which you want the model to remember.", lines=5)
 
     chat_history_state = gr.State()
     clear.click(clear_chat, inputs=[chat_history_state, message], outputs=[chat_history_state, message], queue=False)
     clear.click(lambda: None, None, chatbot, queue=False)
-    submit_click_event = submit.click(fn=user, inputs=[message, chat_history_state], outputs=[message, chat_history_state], queue=True).then(fn=chat, inputs=[chat_history_state, system_msg, max_tokens, temperature, top_p, top_k, repetition_penalty], outputs=[chatbot, chat_history_state, message], queue=True)
-demo.queue(max_size=128, concurrency_count=48)
+
+    submit_click_event = submit.click(
+        fn=user, inputs=[message, chat_history_state], outputs=[message, chat_history_state], queue=True
+    ).then(
+        fn=chat, inputs=[chat_history_state, system_msg, max_tokens, temperature, top_p, top_k, repetition_penalty], outputs=[chatbot, chat_history_state, message], queue=True
+    )
+    stop.click(fn=None, inputs=None, outputs=None, cancels=[submit_click_event], queue=False)
+
+demo.queue(max_size=128, concurrency_count=48).launch(debug=True, server_name="0.0.0.0", server_port=7860)