Update app.py

app.py

@@ -36,13 +36,13 @@ if not torch.cuda.is_available():
 
 
 if torch.cuda.is_available():
-    model_id = "meta-llama/Llama-2-13b-chat-hf"
+    model_id = "ibm/labradorite-13b"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False
 
 
-@spaces.GPU
+@spaces.GPU(enable_queue=True)
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],