Update

app.py

@@ -16,5 +16,12 @@ def chat(message, model, tokenizer):
 
 model, tokenizer = load_model()
 
-iface = gr.Interface(fn=lambda message: chat(message, model, tokenizer), inputs="text", outputs="text")
-iface.launch()
+# Gradio interface to handle text input
+iface = gr.Interface(
+    fn=lambda message: chat(message, model, tokenizer),
+    inputs="text",
+    outputs="text"
+)
+
+# Expose an API endpoint
+iface.launch(server_name="0.0.0.0", server_port=7860, enable_queue=True)