Fixed

app.py

@@ -215,5 +215,10 @@ with gr.Blocks(
     msg.submit(chat, [msg, chatbot], [chatbot, msg])
 
 if __name__ == "__main__":
-    demo.queue()
-    demo.launch(share=False)
+    demo.queue(max_size=20)
+    demo.launch(
+        share=True,
+        server_name="0.0.0.0",
+        server_port=7860,
+        show_error=True
+    )

requirements.txt

@@ -1,3 +1,4 @@
 gradio==4.44.1
 huggingface_hub==0.25.2
 llama-cpp-python==0.2.90
+gradio-client==0.17.0