Update app.py

app.py

@@ -1,10 +1,8 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Initialize the client for ZeroGPU-powered model
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-# Response function
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
     
@@ -28,44 +26,18 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
         response += token
         yield response
 
-# Gradio interface
-with gr.Blocks(css=".gr-box { border-radius: 12px; padding: 16px; }") as demo:
-    gr.Markdown(
-        """
-        # 🤖 Zephyr-7B Chatbot (ZeroGPU Powered)
-        Talk to the `HuggingFaceH4/zephyr-7b-beta` model in real-time using ZeroGPU.
-        Customize generation settings below.
-        """,
-        elem_classes=["gr-box"]
-    )
-
+with gr.Blocks() as demo:
     chatbot = gr.Chatbot(label="Chat", show_copy_button=True, type="messages")
+    system_msg = gr.Textbox(value="You are a helpful assistant.", label="System Message")
+    max_tokens = gr.Slider(1, 2048, value=512, label="Max Tokens")
+    temperature = gr.Slider(0.1, 4.0, value=0.7, label="Temperature")
+    top_p = gr.Slider(0.1, 1.0, value=0.95, label="Top-p")
+    msg_input = gr.Textbox(label="Message", placeholder="Ask me anything...")
 
-    with gr.Row():
-        system_msg = gr.Textbox(
-            label="🧠 System Prompt",
-            value="You are a friendly assistant.",
-            lines=2,
-            interactive=True,
-            scale=2
-        )
-    with gr.Row():
-        max_tokens = gr.Slider(1, 2048, value=512, step=1, label="Max Tokens")
-        temperature = gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature")
-        top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
-
-    msg_input = gr.Textbox(label="💬 Your message", placeholder="Type a message and press Enter...")
-
-    # Bind function to chat
-    def user_submit(user_message, history, system_message, max_tokens, temperature, top_p):
-        return respond(user_message, history, system_message, max_tokens, temperature, top_p)
+    def chat_fn(msg, history, system_msg, max_tokens, temperature, top_p):
+        return respond(msg, history, system_msg, max_tokens, temperature, top_p)
 
-    msg_input.submit(
-        fn=user_submit,
-        inputs=[msg_input, chatbot, system_msg, max_tokens, temperature, top_p],
-        outputs=chatbot
-    )
+    msg_input.submit(chat_fn, [msg_input, chatbot, system_msg, max_tokens, temperature, top_p], chatbot)
 
-# Launch
 if __name__ == "__main__":
     demo.launch()