model_name = "tokyotech-llm/Swallow-70b-instruct-hf"
peft_model= "AIgroup-CVM-utokyohospital/MedSwallow-70b"

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

bnb_config = BitsAndBytesConfig(
            load_in_4bit=True,
            bnb_4bit_quant_type="nf4",
            bnb_4bit_compute_dtype=torch.float16,
        )

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    load_in_8bit=False,
    torch_dtype=torch.float16,
    device_map=device,
        
model = PeftModel.from_pretrained(
    model, 
    peft_model, 
    torch_dtype=torch.float16,
    device_map=device, 
)

@misc{sukeda202470bparameterlargelanguagemodels,
      title={70B-parameter large language models in Japanese medical question-answering}, 
      author={Issey Sukeda and Risa Kishikawa and Satoshi Kodera},
      year={2024},
      eprint={2406.14882},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2406.14882}, 
}