from transformers import BitsAndBytesConfig


nf4_config = BitsAndBytesConfig(
   load_in_4bit=True,
   bnb_4bit_quant_type="nf4",
   bnb_4bit_use_double_quant=True,
   bnb_4bit_compute_dtype=torch.bfloat16
)

model_nf4 = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=nf4_config)