update 1

app.py

@@ -1,3 +1,4 @@
+import spaces
 import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
@@ -15,6 +16,7 @@ class StopOnTokens(StoppingCriteria):
                 return True
         return False
 
+@spaces.GPU
 def predict(message, history):
     history_transformer_format = list(zip(history[:-1], history[1:])) + [[message, ""]]
     stop = StopOnTokens()