Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import os
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 from threading import Thread
-
+import spaces
 # Set an environment variable
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
@@ -30,7 +30,7 @@ h1 {
 tokenizer = AutoTokenizer.from_pretrained("UnfilteredAI/DAN-L3-R1-8B")
 model = AutoModelForCausalLM.from_pretrained("UnfilteredAI/DAN-L3-R1-8B", device_map="auto")
 terminators = [tokenizer.eos_token_id]
-
+@spaces.GPU(duration=30)
 def chat_dan_l3_r1_8b(message: str, history: list, temperature: float, max_new_tokens: int) -> str:
     """
     Generate a streaming response using the DAN-L3-R1-8B model.