Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 from huggingface_hub import InferenceClient, Repository
 import json
+import torch
 
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
@@ -77,4 +78,9 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
+    # Check if CUDA GPU is installed
+    if torch.cuda.is_available():
+        print("CUDA GPU is installed. Running inference on GPU.")
+    else:
+        print("CUDA GPU is not installed. Running inference on CPU.")
     demo.launch()