Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

Yet another python binding for mecab-ko

Human-like summarization and translation papers and articles using OpenAPI

Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

Faker is a Python package that generates fake data for you.

Curation note of NLP datasets

DALL·E Mini - Generate images from a text prompt

Megatron LM 11B on Huggingface Transformers

ChatterBot is a machine learning, conversational dialog engine for creating chat bots

A multilingual dialog corpus

Asian language bart models (En, Ja, Ko, Zh, ECJK)

Package for controllable summarization

OpenChat: Easy to use opensource chatting framework via neural networks

Kiwi(지능형 한국어 형태소 분석기)

Opensource chatbot framework

A Deep Learning based project for creating line art portraits.

Japanese GPT2 Generation Model

newspaper3k is a news, full-text, and article metadata extraction in Python 3. Advanced docs:

Transformer implementation speciaized in speech recognition tasks using Pytorch.

A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code

Kobart model on Huggingface transformers

KSS: Korean String processing Suite

Abstractive summarization using Bert2Bert framework.

PyTorch implementation of automatic speech recognition models.

Experiments with spiking neural networks (SNNs) in PyTorch. See https://github.com/BINDS-LAB-UMASS/bindsnet for the successor to this project.

개인적으로 수집한 한국어 NLP용 말뭉치 모음

100 Must-Read NLP Papers

👦 👧 Technical-Interview guidelines written for those who started studying programming. I wish you all the best. 👾

Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.

A python binding for mecab-ko