LOGO

Beomi

AI/ML GDE. Korean AI/NLP Researcher and creator of multiple Korean PLMs. Focused on advancing Open LLMs.
Seoul, South Korea[email protected]

Github Data

Followers 814
Following 0

Links

https://x.com/__Beomi__https://junbuml.ee

AI Project

Public repos: 122Public gists: 44

InfiniTransformer

Unofficial PyTorch/๐Ÿค—Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
star: 295fork: 20
language: Python
created at: 2024-04-12
updated at: 2024-08-10

Gemma-EasyLM

Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)
star: 38fork: 11
language: Python
created at: 2024-03-02
updated at: 2024-07-30

BitNet-Transformers

0๏ธโƒฃ1๏ธโƒฃ๐Ÿค— BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture
star: 252fork: 30
language: Python
created at: 2023-10-19
updated at: 2024-06-27

ko-lm-evaluation-harness

Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adc
star: 57fork: 16
language: Python
created at: 2023-07-24
updated at: 2024-08-09

KoAlpaca

KoAlpaca: ํ•œ๊ตญ์–ด ๋ช…๋ น์–ด๋ฅผ ์ดํ•ดํ•˜๋Š” ์˜คํ”ˆ์†Œ์Šค ์–ธ์–ด๋ชจ๋ธ
star: 1.5Kfork: 238
language: Jupyter Notebook
created at: 2023-03-18
updated at: 2024-08-11

easy-lm-trainer

๐Ÿค— ์ตœ์†Œํ•œ์˜ ์„ธํŒ…์œผ๋กœ LM์„ ํ•™์Šตํ•˜๊ธฐ ์œ„ํ•œ ์ƒ˜ํ”Œ์ฝ”๋“œ
star: 57fork: 9
language: Python
created at: 2022-08-17
updated at: 2024-04-04