Update app.py

app.py

@@ -15,7 +15,7 @@ device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 model = AutoModelForCausalLM.from_pretrained(
   'kakaobrain/kogpt', revision='KoGPT6B-ryan1.5b',cache_dir='./model_dir/',
   pad_token_id=tokenizer.eos_token_id,
-  torch_dtype=torch.float16, low_cpu_mem_usage=False
+  torch_dtype=torch.float16, low_cpu_mem_usage=True
 ).to(device=device, non_blocking=True)
 _ = model.eval()