Want to use CPU for falcon7b

My system runs out of memory on GPU. But I want just to test if it works and want to load it on CPU. How do I do that?
Adding ‘’‘device = torch.device(‘cpu’)’‘’ before loading model doesn’t help
It crashes here:

model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    quantization_config=bnb_config,
    device_map="auto",
    trust_remote_code=True,
)