LOGO

Beomi

AI/ML GDE @ml-gde. Korean AI/NLP Researcher and creator of multiple Korean PLMs. Focused on advancing Open LLMs.
Seoul, South Korea

Github Data

Followers 883
Following 0

Links

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

AI Project

Public repos: 125Public gists: 45

InfiniTransformer

Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
star: 347fork: 30
language: Python
created at: 2024-04-12
updated at: 2024-11-24

Gemma-EasyLM

Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)
star: 45fork: 11
language: Python
created at: 2024-03-02
updated at: 2024-09-15

BitNet-Transformers

0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture
star: 280fork: 33
language: Python
created at: 2023-10-19
updated at: 2024-11-23

ko-lm-evaluation-harness

Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adc
star: 69fork: 19
language: Python
created at: 2023-07-24
updated at: 2024-10-31

KoAlpaca

KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델 (KoAlpaca: An open-source language model to understand Korean instructions)
star: 1.5Kfork: 238
language: Jupyter Notebook
created at: 2023-03-18
updated at: 2024-11-21

easy-lm-trainer

🤗 최소한의 세팅으로 LM을 학습하기 위한 샘플코드
star: 57fork: 9
language: Python
created at: 2022-08-17
updated at: 2024-04-04