LLaMA 3.1 8B Instruct - Healthcare Fine-tuned Model
This is a model that fine-tuned the Llama-3.1-8B-Instruct model from Unidocs using Healthcare data.
์ ๋๋ฅ์ค(์ฃผ)์์ Llama-3.1-8B-Instruct ๋ชจ๋ธ์ Healthcare ๋ฐ์ดํฐ๋ก ๋ฏธ์ธ์กฐ์ ํ ๋ชจ๋ธ์
Model Description
sLLM model used in Unidoc's ezMyAIDoctor, released on October 16, 2024 as a result of the AIDC-HPC project
of the Artificial Intelligence Industry Convergence Business Group (AICA)
meta-llama/Llama-3.1-8B-Instruct wiki, kowiki, super-large AI healthcare question-answer data,
A model that has been pretrained (Full Finetuning) by referring to the super-large AI corpus with improved Korean performance,
and the medical and legal professional book corpus.
์ ๋๋ฅ์ค(์ฃผ)์ ezMyAIDoctor์์ ์ฌ์ฉ๋๋ sLLM ๋ชจ๋ธ๋ก ์ธ๊ณต์ง๋ฅ์ฐ์
์ตํฉ์ฌ์
๋จ(AICA)์ AIDC-HPC ์ฌ์
์ ๊ฒฐ๊ณผ๋ก 2024๋
10์ 16์ผ ๊ณต๊ฐํจ
meta-llama/Llama-3.1-8B-Instruct์ wiki, kowiki, AIHub(aihub.or.kr)์ (์ด๊ฑฐ๋AI ํฌ์ค์ผ์ด ์ง์์๋ต๋ฐ์ดํฐ,
ํ๊ตญ์ด ์ฑ๋ฅ์ด ๊ฐ์ ๋ ์ด๊ฑฐ๋ AI ๋ง๋ญ์น, ์๋ฃ/๋ฒ๋ฅ ์ ๋ฌธ์์ ๋ง๋ญ์น)๋ฅผ ์ฐธ๊ณ ํ์ฌ Pretrain(Full Finetuning)๋ ๋ชจ๋ธ์
Intended Uses & Limitations
The model is designed to assist with healthcare-related queries and tasks.
However, it should not be used as a substitute for professional medical advice, diagnosis, or treatment.
Always consult with a qualified healthcare provider for medical concerns.
์ด ๋ชจ๋ธ์ Healthcare ๊ด๋ จ ์ง์ ๋ฐ ์์
์ ์ง์ํ๋๋ก ์ค๊ณ๋์์ต๋๋ค.
๊ทธ๋ฌ๋ ์ ๋ฌธ์ ์ธ ์ํ์ ์กฐ์ธ, ์ง๋จ ๋๋ ์น๋ฃ๋ฅผ ๋์ฒดํ๋ ๋ฐ ์ฌ์ฉ๋์ด์๋ ์ ๋ฉ๋๋ค.
์๋ฃ ๊ด๋ จ ๋ฌธ์ ๋ ํญ์ ์๊ฒฉ์ ๊ฐ์ถ ์๋ฃ ์๋น์ค ์ ๊ณต์์ ์์ํ์ญ์์ค.
Training Data
The model was fine-tuned on a proprietary healthcare dataset.
Due to privacy concerns, details of the dataset cannot be disclosed.
wiki, kowiki ๋ฐ์ดํฐ ์ด์ธ
๊ณผํ๊ธฐ์ ์ ๋ณดํต์ ๋ถ, ํ๊ตญ์ง๋ฅ์ ๋ณด์ฌํ์งํฅ์์์ ๊ด๋ฆฌํ๊ณ ์๋ AIHub์
- ์ด๊ฑฐ๋AI ํฌ์ค์ผ์ด ์ง์์๋ต๋ฐ์ดํฐ
- ํ๊ตญ์ด ์ฑ๋ฅ์ด ๊ฐ์ ๋ ์ด๊ฑฐ๋ AI ๋ง๋ญ์น
- ์๋ฃ, ๋ฒ๋ฅ ์ ๋ฌธ์์ ๋ง๋ญ์น
๋ฑ์ ํ์ฉํจ
Training Procedure
Full fine-tuning was performed on the base LLaMA 3.1 8B Instruct model using the healthcare dataset.
Healthcare ๋ฐ์ดํฐ ์ธํธ๋ฅผ ์ฌ์ฉํ์ฌ ๊ธฐ๋ณธ LLaMA 3.1 8B Instruct ๋ชจ๋ธ์์ ์ ์ฒด ๋ฏธ์ธ ์กฐ์ ์ ์ํํ์ต๋๋ค.
Evaluation Results
Accuracy by category of mmlu benchmark
category | Accuracy |
---|---|
anatomy | 0.68 (92/135) |
clinical_knowledge | 0.75 (200/265) |
college_medicine | 0.68 (117/173) |
medical_genetics | 0.70 (70/100) |
professional_medicine | 0.76 (208/272) |
All Accuracy Mean value: 0.72
Use with transformers
Starting with transformers >= 4.43.1
onward, you can run conversational inference using the Transformers pipeline
abstraction or by leveraging the Auto classes with the generate()
function.
Make sure to update your transformers installation via pip install --upgrade transformers
.
import transformers
import torch
model_id = "unidocs/llama-3.1-8b-komedic-instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
messages = [
{"role": "system", "content": "๋น์ ์ ์๋ฃ์ ๋ฌธ๊ฐ์
๋๋ค. ์ง๋ณ์ ์ ์, ์์ธ, ์ฆ์, ๊ฒ์ง, ์ง๋จ, ์น๋ฃ, ์ฝ๋ฌผ, ์์ด, ์ํ ์ธก๋ฉด์์ ๋ต๋ณํด ์ฃผ์ธ์"},
{"role": "user", "content": "๊ณต๋ณตํ๋น์ด 120์ด์์ธ ๊ฒฝ์ฐ ์ 1ํ ๋น๋จ์ ์ 2ํ ๋น๋จ ํ์๋ ๊ฐ๊ฐ ์ด๋ป๊ฒ ์น๋ฃ๋ฅผ ๋ฐ์์ผ ํ๋์?"},
]
outputs = pipeline(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
Note: You can also find detailed recipes on how to use the model locally, with torch.compile()
, assisted generations, quantised and more at huggingface-llama-recipes
Limitations and Bias
This model may produce biased or inaccurate results. It should not be solely relied upon for critical healthcare decisions.
The model's knowledge is limited to its training data and cut-off date.
It may exhibit biases present in the training data.
The model may occasionally produce incorrect or inconsistent information.
๋ชจ๋ธ์ ์ง์์ ํ๋ จ ๋ฐ์ดํฐ์ ๋ง๊ฐ์ผ๋ก ์ ํ๋ฉ๋๋ค.
ํ๋ จ ๋ฐ์ดํฐ์ ํธํฅ์ด ์์ ์ ์์ต๋๋ค.
๋ชจ๋ธ์ ๊ฐ๋ ์๋ชป๋๊ฑฐ๋ ์ผ๊ด๋์ง ์์ ์ ๋ณด๋ฅผ ์์ฑํ ์ ์์ต๋๋ค.
์ด ๋ชจ๋ธ์ ํธํฅ๋๊ฑฐ๋ ๋ถ์ ํํ ๊ฒฐ๊ณผ๋ฅผ ์์ฑํ ์ ์์ต๋๋ค. ์ค์ํ ์๋ฃ ๊ฒฐ์ ์ ์ด ๋ชจ๋ธ์๋ง ์์กดํด์๋ ์ ๋ฉ๋๋ค.
Legal Disclaimer
The model developers and distributors bear no legal responsibility for any consequences arising from the use of this model.
This includes any direct, indirect, incidental, special, punitive, or consequential damages resulting from the model's output.
By using this model, users assume all risks that may arise, and the responsibility for verifying and appropriately using the model's output lies solely with the user.
This model cannot substitute for medical advice, diagnosis, or treatment, and qualified healthcare professionals should always be consulted for medical decisions.
This disclaimer applies to the maximum extent permitted by applicable law.
๋ฒ์ ์ฑ ์ ๋ฉด์ฑ ์กฐํญ
๋ณธ ๋ชจ๋ธ์ ์ฌ์ฉ์ผ๋ก ์ธํด ๋ฐ์ํ๋ ๋ชจ๋ ๊ฒฐ๊ณผ์ ๋ํด ๋ชจ๋ธ ๊ฐ๋ฐ์ ๋ฐ ๋ฐฐํฌ์๋ ์ด๋ ํ ๋ฒ์ ์ฑ
์๋ ์ง์ง ์์ต๋๋ค.
์ด๋ ๋ชจ๋ธ์ ์ถ๋ ฅ์ผ๋ก ์ธํ ์ง์ ์ , ๊ฐ์ ์ , ์ฐ๋ฐ์ , ํน์ํ, ์ง๋ฒ์ ๋๋ ๊ฒฐ๊ณผ์ ์ํด๋ฅผ ํฌํจํฉ๋๋ค.
์ฌ์ฉ์๋ ๋ณธ ๋ชจ๋ธ์ ์ฌ์ฉํจ์ผ๋ก์จ ๋ฐ์ํ ์ ์๋ ๋ชจ๋ ์ํ์ ๊ฐ์ํ๋ฉฐ, ๋ชจ๋ธ์ ์ถ๋ ฅ์ ๋ํ ๊ฒ์ฆ ๋ฐ ์ ์ ํ ์ฌ์ฉ์ ๋ํ ์ฑ
์์ ์ ์ ์ผ๋ก ์ฌ์ฉ์์๊ฒ ์์ต๋๋ค.
๋ณธ ๋ชจ๋ธ์ ์ํ์ ์กฐ์ธ, ์ง๋จ, ๋๋ ์น๋ฃ๋ฅผ ๋์ฒดํ ์ ์์ผ๋ฉฐ, ์๋ฃ ๊ด๋ จ ๊ฒฐ์ ์ ๋ด๋ฆด ๋๋ ๋ฐ๋์ ์๊ฒฉ์ ๊ฐ์ถ ์๋ฃ ์ ๋ฌธ๊ฐ์ ์๋ดํด์ผ ํฉ๋๋ค.
์ด ๋ฉด์ฑ
์กฐํญ์ ๊ด๋ จ ๋ฒ๋ฅ ์ด ํ์ฉํ๋ ์ต๋ ๋ฒ์ ๋ด์์ ์ ์ฉ๋ฉ๋๋ค.
Model Card Contact
์ ์ ([email protected]), ๊น์ง์ค([email protected])
Additional Information
For more details about the base model, please refer to the original LLaMA 3.1 documentation.
- Downloads last month
- 216