Michael Han

5X faster 60% less memory QLoRA finetuning

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

Interactive roadmaps, guides and other educational content to help developers grow in their careers.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)

Unsloth fine-tuning resources.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

freeCodeCamp.org's open-source codebase and curriculum. Learn to code for free.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

https://docs.openwebui.com

Open source, production-ready animation and gesture library for React

Config files for my GitHub profile.

GPT4All: Chat with Local LLMs on Any Device

Utils for Unsloth https://github.com/unslothai/unsloth

No description.

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Use Hugging Face with JavaScript

The original local LLM interface. Text, vision, tool-calling, training, and more. 100% offline.

250+ Fine-tuning & RL Notebooks on Google Colab and Kaggle.

State-of-the-Art Text Embeddings

Kernels & AI inference engine for mobile devices.

21 Lessons, Get Started Building with Generative AI

PyTorch native quantization and sparsity for training and inference

No description.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

A high-throughput and memory-efficient inference and serving engine for LLMs

Train transformer language models with reinforcement learning.

No description.

No description.

No description.

Sbeta

A collection of example Framer Plugins.

A huge collection of SVG logos

Concise, consistent, and legible badges in SVG and raster format

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

No description.