Update app.py

app.py

@@ -12,7 +12,7 @@ device = 0 if torch.cuda.is_available() else -1
 # Define the function to generate responses
 @spaces.GPU(duration = 190)
 def generate_response(user_input, history):
-    pipe = pipeline("text-generation", model="explorewithai/ChatFrame-Uncensored-Instruct-Small")
+    pipe = pipeline("text-generation", model="explorewithai/ChatFrame-Uncensored-Instruct-Small", device = device)
     messages = [
         {"role": "user", "content": user_input},
     ]