---
library_name: peft
license: cc-by-nc-sa-4.0
tags:
- medical
---
⚠️⚠️⚠️ Only for research purpose. Do not use it for medical purpose. ⚠️⚠️⚠️

# MedSwallow-70B🏥

[東工大Swallow](https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf)をベースモデルとし, 医療Q&AデータセットでInstruction Tuningを施した医療ドメインの日本語LLMです.

チューニングには独自で用意した米国医師国家試験(USMLE)を和訳したQ&Aデータセットを用いました.


MedSwallow is a Japanese medical LLM for medical question-answering.

MedSwallow is based on [Swallow-70B](https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf) and has passed instruction tuning with USMLE dataset translated in Japanese by our own.


## Training procedure

The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16

### Framework versions
- PEFT 0.4.0


## License

ライセンスは非商用ライセンスです.

Non-commercial.


## Usage

```
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, 
)

```


## Benchmark

See also [Japanese Medical Language Model Evaluation Harness](https://github.com/stardust-coder/japanese-lm-med-harness).

- IgakuQA (in English): 
- IgakuQA (in Japanese): 
- MedQA (in English) :
- MedQA (in Japanese) :


## How to cite
```
coming soon...
```