Update app.py

app.py

@@ -3,6 +3,9 @@ import gradio as gr
 import torch
 from PIL import Image
 from transformers import AutoModel, AutoTokenizer
+import spaces
+
+device="cuda"
 
 # Load the model and tokenizer
 model = AutoModel.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5', trust_remote_code=True, torch_dtype=torch.float16)
@@ -11,6 +14,7 @@ tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5', trust_
 model.eval()
 
 # Define a function to generate a response
+@spaces.GPU
 def generate_response(image, question):
     msgs = [{'role': 'user', 'content': question}]
     res = model.chat(