flowpoint

gdlog

Voyager

An Open-Ended Embodied Agent with Large Language Models

krazyworld

krazy grid world

babyai

BabyAI platform. A testbed for training agents to understand and execute language commands.

Nuitka

Nuitka is a Python compiler written in Python. It's fully compatible with Python 2.6, 2.7, 3.4-3.12. You feed it your Python app, it does a lot of clever things, and spits out an executable or extension module.

purejaxrl

Really Fast End-to-End Jax RL Implementations

xland-minigrid

JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️

act

Run your GitHub Actions locally 🚀

minihf

MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user develop their prompts into full models.

bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

gymnax

RL Environments in JAX 🌍

Video-Pre-Training

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

STEVE-1

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

EldenRL

Reinforcement Learning for Elden Ring on Windows11

SoulsGym

Gymnasium extension for DarkSouls III, Elden Ring, and other Souls games

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

PokemonRedExperiments

Playing Pokemon Red with Reinforcement Learning

meme-search-engine

Local CLIP search over meme libraries

video2dataset

Easily create large video dataset from video urls

clip-video-encode

Easily compute clip embeddings from video frames

webdataset

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

laion-prepro

Get hundred of million of image+url from the crawling at home dataset and preprocess them

clip-retrieval

Easily compute clip embeddings and build a clip retrieval system with them

OBELICS

Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.

Big-Interleaved-Dataset

Big-Interleaved-Dataset

open_flamingo

An open-source framework for training large multimodal models.

MS-AMP

Microsoft Automatic Mixed Precision Library

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

framework-reproducibility

Providing reproducibility in deep learning frameworks