Stars
Library for reading and processing ML training data.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Implementation of Diffusion Transformer (DiT) in JAX
Code release for paper "Autonomous Improvement of Instruction Following Skills via Foundation Models" | CoRL 2024
A simple, performant and scalable Jax LLM!
TPU pod commander is a package for managing and launching jobs on Google Cloud TPU pods.
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC