c

app.py

@@ -127,6 +127,20 @@ def respond(message, history):
         out = model.generate(**inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)
     return tokenizer.decode(out[0], skip_special_tokens=True)
 
-iface = gr.ChatInterface(fn=respond, title="Gemma-ZeroGPU Demo")
+iface = gr.ChatInterface(
+    fn=respond,
+    title="Gemma-ZeroGPU Demo",
+    chatbot=gr.Chatbot(
+        type="messages",
+        height=600,
+        show_copy_button=True,
+        show_share_button=True
+    )
+)
+
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=True
+    )