Update app.py

app.py

@@ -30,7 +30,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
+model_id = "prithivMLmods/Llama-Express.1"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -40,7 +40,7 @@ model = AutoModelForCausalLM.from_pretrained(
 model.eval()
 
 
-@spaces.GPU(duration=120)
+@spaces.GPU(duration=60)
 def generate(
     message: str,
     chat_history: list[dict],