Update app.py

app.py

@@ -45,7 +45,7 @@ model_id = "CardinalOperations/ORLM-LLaMA-3-8B"
 # )
 # model.eval()
 
-subprocess.run(f'huggingface-cli download {model_id} --local_dir ./local_model',  shell=True)
+subprocess.run(f'huggingface-cli download {model_id} --local-dir ./local_model',  shell=True)
 model = LLM(model='./local_model', tensor_parallel_size=torch.cuda.device_count())
 print("init model done.")