LLM fine-tuning
with Healthcare data 이론 및 실습
2024-11-14, 10:00 ~ 12:00
Seongsu Bae, Sujeong Im
KAIST AI @ Edlab (Advised by Edward Choi)
KoSAIM 2024 개발자를 위한 의료 AI 심화교육 II
Speaker Bio
Sujeong Im (임수정)
Education
��Research Interests
Seongsu Bae (배성수)
Education
Research Interests
Asclepius-Meta-Llama-3-8B
How can we build an instruction-following LLM in the clinical domain?
Prepare a pre-trained large language model
Pre-training on clinical corpus for domain adaptation
Perform supervised fine-tuning using domain-specific clinical instruction data
Asclepius-Meta-Llama-3-8B
use Meta-Llama3-8B model
Pre-training (1 epoch): 2h 59m with 4x A100 80G
dataset: 158k synthetic clinical notes
Instruction fine-tuning (3 epoch): 30h 41m with 4x A100 80G
dataset: 158k clinical instruction-response pairs with synthetic notes
How can we build an instruction-following LLM in the clinical domain?
Prepare a pre-trained large language model
Pre-training on clinical corpus for domain adaptation
Perform supervised fine-tuning using domain-specific clinical instruction data
(실습) Asclepius-phi-2
use phi-2 (2.7B) model
LLM fine-tuning (QLoRA) on a T4 GPU (16 GiB), using a sampled set from 158k clinical instruction-response pairs with synthetic notes.
Deep learning memory layout
Can You Run it?
LoRA (Hu and Shen et al., 2021)
QLoRA (Dettmers and Pagnoni et al., 2023)
Parameter-Efficient Fine-Tuning (PEFT)
Colab 실습 파트
Colab 실습 개요
Colab 실습 주의사항
Colab 실습 링크
Thank you :D
If you require any further information, feel free to contact us: seongsu@kaist.ac.kr, sujeongim@kaist.ac.kr
KoSAIM 2024 개발자를 위한 의료 AI 심화교육 II