Highlights
Starred repositories
《Reinforcement Learning from Human Feedback》繁體中文全譯本+每章互動實驗 | Unofficial zh-TW community translation of the RLHF Book with interactive labs
This repository contains demos I made with the Transformers library by HuggingFace.
Official repository for the Twinkle AI Late-Night Study Session. Features hands-on Jupyter notebooks, slides, and code for our book club on "Hands-On Large Language Models"
Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.
The agent that grows with you
Build local voice agents with open-source models
Building and Scaling RL environments in the age of LLMs
A course on context engineering with code agents.
Practical, Colab-friendly notebooks for fine-tuning and running audio AI models
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models
Dissecting the Duck's Innards — A DuckDB-based course on the Design and Implementation of Database System Internals
Tabular Database Systems — A DuckDB-based course on the fundamentals of relational DBMSs and SQL
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
Materials for the LLM Engineering Essentials course
🇹🇼 讓全世界完整認識台灣 | An open-source, AI-friendly knowledge base about Taiwan
AI agents running research on single-GPU nanochat training automatically
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
A companion to CMU professor Zico Kolter's Intro to Modern AI. Learn the basics of machine learning, then train your own LLM from scratch.
Forge-CuTe-Py: A PyTorch-native CuTe DSL kernel laboratory for correctness, benchmarking, and profiling.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
The Missing Semester of Your CS Education 📚
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.