Update app.py

app.py

@@ -6,7 +6,7 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
 import torch
 from threading import Thread
-
+import spaces
 
 # Load model directly
 device = "cuda" if torch.cuda.is_available() else "cpu"
@@ -14,6 +14,7 @@ tokenizer = AutoTokenizer.from_pretrained("Navid-AI/Mulhem-1-Mini", token=os.get
 model = AutoModelForCausalLM.from_pretrained("Navid-AI/Mulhem-1-Mini", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2", token=os.getenv("HF_TOKEN")).to(device)
 streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
+@spaces.GPU
 def respond(
     message,
     history: list[tuple[str, str]],