Update app.py

app.py

@@ -1,3 +1,4 @@
+import spaces
 import gradio as gr
 
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -18,6 +19,7 @@ class ModelProcessor:
         # Set padding token as end-of-sequence token
         self.tokenizer.pad_token = self.tokenizer.eos_token
 
+    @spaces.GPU
     @torch.inference_mode()
     def process_data_and_compute_statistics(self, prompt):
         # Tokenize the prompt and move to the device