Update app.py

app.py

@@ -1,10 +1,11 @@
 import gradio as gr
 from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+import spaces
 
 # Load model with 8-bit precision
 model_name = "yasserrmd/SmolLM2-156M-synthetic-dlp"
 model = AutoModelForCausalLM.from_pretrained(
-    model_name, 
+    model_name,
     load_in_8bit=True
 )
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -16,6 +17,7 @@ generator = pipeline(
     tokenizer=tokenizer
 )
 
+@spaces.GPU
 def chat_assistant(chat_history, user_input):
     """Generate a response based on user input and chat history."""