Update app.py

app.py

@@ -7,7 +7,7 @@ import torch
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 tokenizer = AutoTokenizer.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True,low_cpu_mem_usage=True)
 
 # Move the model to the GPU if available
 model.to(device)