Update app.py

app.py

@@ -5,7 +5,7 @@ import spaces
 # Load model and tokenizer
 model_name = "yuchenlin/Rex-v0.1-0.5B"
 
-device = "cpu" # the device to load the model onto
+device = "cuda" # the device to load the model onto
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, rex_size=3)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -13,7 +13,7 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 model.to(device)
 
-# @spaces.GPU(enable_queue=True)
+@spaces.GPU(enable_queue=True)
 def respond(
     message,
     history: list[tuple[str, str]],