Update app.py

app.py

@@ -4,6 +4,7 @@ os.environ["GRADIO_ANALYTICS_ENABLED"] = "False"
 
 import gradio as gr
 import torch
+import spaces
 from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -45,4 +46,8 @@ demo = gr.Interface(
     title="Hinglish reply tester",
     flagging_mode="never", analytics_enabled=False,
 )
-demo.queue(default_concurrency_limit=1).launch()
+demo.queue(default_concurrency_limit=1).launch()
+
+@spaces.GPU
+def predict(input_data):
+    return "foo"