Update app.py

app.py

@@ -26,8 +26,7 @@ model = LlamaForCausalLM.from_pretrained(
     quantization_config=quant_config
 )
 
-config = PeftConfig.from_pretrained(lora_name, device="cpu")
-model = PeftModel.from_pretrained(model, lora_name, config=config)
+model = PeftModel.from_pretrained(model, lora_name, device_map="cpu")
 
 model = model.to("cuda")