σ-GPT: A New Approach to Autoregressive Models

Sparse autoencoders

Named Tensors for Legible Deep Learning in JAX

Optax is a gradient processing and optimization library for JAX.

Orbax provides common utility libraries for JAX users.

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Flax is a neural network library for JAX that is designed for flexibility.

LLM training in simple, raw C/CUDA

Ongoing research training transformer models at scale

A massively parallel, optimal functional runtime in Rust

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

Kolmogorov Arnold Networks

The official implementation of Diffusion-KTO: Aligning Diffusion Models by Optimizing Human Utility

A native PyTorch Library for large model training

Rust bindings for the Python interpreter

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

Firefox user.js for speed, privacy, and security. Your favorite browser, but better.

Unlock custom brushes, natural fill effects and intuitive hatching in p5.js

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

🔎 📈 🐍 💰 Backtest trading strategies in Python.

Use your tablet as graphic tablet/touch screen on your computer.

A new markup-based typesetting system that is powerful and easy to learn.

Pocket Kitchen | Node.js & Express web app and MongoDB data pipleline for presenting actionable food waste prevention insights

Minimalist ML framework for Rust

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

🔊 Text-Prompted Generative Audio Model