This is your work, valued
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)
1.6kKcBERT. 🤗 Pretrained BERT model & WordPiece tokenizer trained on Korean Comments 한국어 댓글로 프리트레이닝한 BERT 모델과 데이터셋
492InfiniTransformer. Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
376BitNet-Transformers. 0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture
316KcELECTRA. 🤗 Korean Comments ELECTRA: 한국어 댓글로 학습한 ELECTRA 모델
265cite.gg. 🔍 우리가 읽을 논문을 찾아서, Cite.GG
89ko-lm-evaluation-harness. Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adc
81easy-lm-trainer. 🤗 최소한의 세팅으로 LM을 학습하기 위한 샘플코드
59simple_bank_korea. simple crawler for Korean banks with Transactions
58Gemma-EasyLM. Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)
50KcBERT-Finetune. KcBERT/KcELECTRA Fine Tune Benchmarks code (forked from https://github.com/monologg/KoELECTRA/tree/master/finetune)
47pypapago. 🐧[Archived][Unofficial] Python wrapper for Papago translation service
47aws-lambda-py3. Pre-compiled Python3(3.6+) packages for AWS Lambda layers
29transformers-language-modeling. Train 🤗transformers with DeepSpeed: ZeRO-2, ZeRO-3
23irkshop. Django Shopping Mall WebSite for IRK / DEMO:
17gptpy. GPTPy: Your kind Python guide, powered by AI to fix errors and explain code
13data_camp_wcr. 파이썬을 활용한 실전 웹크롤링 CAMP 강의 1-2기 소스코드
11data_camp_wcr_3. 파이썬을 활용한 실전 웹크롤링 CAMP 3기 소스코드
10exbert-transformers. exBERT on Transformers🤗
10django-tube. 장고걸스 서울 튜토리얼 미니시리즈: DjangoTube
9where-is-my-customs. 내 통관은 어디쯤? 카카오톡 봇
8SlideShare_Character_Updater. Prevents [SlideShare Korean(or UTF-8 langs) Character "Blank"] phenomenon
7naverNewsContentsCrawler. naverNewsContentsCrawler
7beomi.github.io_2019. Beomi's Tech Blog (Deprecated)
7megatronlm_dataset_autotokenizer. Megatron-LM/GPT-NeoX compatible Text Encoder with 🤗Transformers AutoTokenizer.
6Wifibucks. KT Starbucks Wi-Fi Auto Connector
6beomi.github.io. Beomi's Tech Blog (HTML Only)
5s3-direct-uploader-demo. Direct S3 Upload with Lambda Demo
5ssafy-2024-frontend. SSAFY 2024 겨울학기 FE Deploy 기초 레포
4deepo-nlp. Dockerfile for NLP(Korean) based on Deepo
4ssafy-2024-backend. SSAFY 2024 겨울학기 BE Deploy 기초 레포
3typora-s3-uploader. CLI file/img S3 uploader for Typora
3kb_transaction. KB 국민은행 거래내역 조회
3pytorch-tpu-transformers. Python
2Eigen-MoRA. Eigen-MoRA: MoRA with Eigenvector based non-param projection
2ssafy-ai-chatbot-demo-1. TypeScript
2alpaca-lora. Instruct-tune LLaMA on consumer hardware
1kogpt. KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)
1beomi.net. Redirection(URL SHORTENER)
1transformers-pytorch-gpu. 💡 Docker image for Huggingface 🤗 Transformers + GPU + Jupyter notebook + OhMyZsh
1SmartSpamFilter-QnA. Smart Spam Filter QnA
1lambda-requirements-builder. Simple Script Example to Build Lambda Layers (with Python3)
1KcBERT-nsmc. Naver movie review sentiment classification with KcBERT
1Evergreen-SBERT. 🌲Evergreen-SBERT: Extensible Sentence BERT with Up-to-Date Corpora
1peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
1kor2vec. OOV없이 빠르고 정확한 한국어 Embedding 라이브러리
1WebCrawlerExamples. WebCrawler 강의 예제
1NetworkAutoLogin. Automagically logs into to Captive Portal Networks
1