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

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app

A toolkit for developing and comparing reinforcement learning algorithms.

Ultralytics YOLO11 🚀

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

PyTorch package for the discrete VAE used for DALL·E.

Train transformer language models with reinforcement learning.

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

A collection of libraries to optimise AI model performances

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Count the MACs / FLOPs of your PyTorch model.

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

Pytorch library for fast transformer implementations

An offline deep reinforcement learning library

Code for the paper Fine-Tuning Language Models from Human Preferences

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

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

Expanding natural instructions

[NeurIPS'19] Deep Equilibrium Models

Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools.

Code for conservative Q-learning

Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch

SBX: Stable Baselines Jax (SB3 + Jax)