Seoul, South Korea

Junbum Lee

Elite
@Beomi

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

KoAlpaca. KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델 (KoAlpaca: An open-source language model to understand Korean instructions)

1.6k

KcBERT. 🤗 Pretrained BERT model & WordPiece tokenizer trained on Korean Comments 한국어 댓글로 프리트레이닝한 BERT 모델과 데이터셋

492

InfiniTransformer. Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

376

BitNet-Transformers. 0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture

316

KcELECTRA. 🤗 Korean Comments ELECTRA: 한국어 댓글로 학습한 ELECTRA 모델

265

cite.gg. 🔍 우리가 읽을 논문을 찾아서, Cite.GG

89

ko-lm-evaluation-harness. Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adc

81

easy-lm-trainer. 🤗 최소한의 세팅으로 LM을 학습하기 위한 샘플코드

59

simple_bank_korea. simple crawler for Korean banks with Transactions

58

Gemma-EasyLM. Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)

50

KcBERT-Finetune. KcBERT/KcELECTRA Fine Tune Benchmarks code (forked from https://github.com/monologg/KoELECTRA/tree/master/finetune)

47

pypapago. 🐧[Archived][Unofficial] Python wrapper for Papago translation service

47

aws-lambda-py3. Pre-compiled Python3(3.6+) packages for AWS Lambda layers

29

transformers-language-modeling. Train 🤗transformers with DeepSpeed: ZeRO-2, ZeRO-3

23

irkshop. Django Shopping Mall WebSite for IRK / DEMO:

17

gptpy. GPTPy: Your kind Python guide, powered by AI to fix errors and explain code

13

data_camp_wcr. 파이썬을 활용한 실전 웹크롤링 CAMP 강의 1-2기 소스코드

11

data_camp_wcr_3. 파이썬을 활용한 실전 웹크롤링 CAMP 3기 소스코드

10

exbert-transformers. exBERT on Transformers🤗

10

django-tube. 장고걸스 서울 튜토리얼 미니시리즈: DjangoTube

9

where-is-my-customs. 내 통관은 어디쯤? 카카오톡 봇

8

SlideShare_Character_Updater. Prevents [SlideShare Korean(or UTF-8 langs) Character "Blank"] phenomenon

7

naverNewsContentsCrawler. naverNewsContentsCrawler

7

beomi.github.io_2019. Beomi's Tech Blog (Deprecated)

7

megatronlm_dataset_autotokenizer. Megatron-LM/GPT-NeoX compatible Text Encoder with 🤗Transformers AutoTokenizer.

6

Wifibucks. KT Starbucks Wi-Fi Auto Connector

6

beomi.github.io. Beomi's Tech Blog (HTML Only)

5

s3-direct-uploader-demo. Direct S3 Upload with Lambda Demo

5

ssafy-2024-frontend. SSAFY 2024 겨울학기 FE Deploy 기초 레포

4

deepo-nlp. Dockerfile for NLP(Korean) based on Deepo

4

ssafy-2024-backend. SSAFY 2024 겨울학기 BE Deploy 기초 레포

3

typora-s3-uploader. CLI file/img S3 uploader for Typora

3

kb_transaction. KB 국민은행 거래내역 조회

3

pytorch-tpu-transformers. Python

2

Eigen-MoRA. Eigen-MoRA: MoRA with Eigenvector based non-param projection

2

ssafy-ai-chatbot-demo-1. TypeScript

2

alpaca-lora. Instruct-tune LLaMA on consumer hardware

1

kogpt. KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)

1

beomi.net. Redirection(URL SHORTENER)

1

transformers-pytorch-gpu. 💡 Docker image for Huggingface 🤗 Transformers + GPU + Jupyter notebook + OhMyZsh

1

SmartSpamFilter-QnA. Smart Spam Filter QnA

1

lambda-requirements-builder. Simple Script Example to Build Lambda Layers (with Python3)

1

KcBERT-nsmc. Naver movie review sentiment classification with KcBERT

1

Evergreen-SBERT. 🌲Evergreen-SBERT: Extensible Sentence BERT with Up-to-Date Corpora

1

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

1

kor2vec. OOV없이 빠르고 정확한 한국어 Embedding 라이브러리

1

WebCrawlerExamples. WebCrawler 강의 예제

1

NetworkAutoLogin. Automagically logs into to Captive Portal Networks

1
48
Apply