SatireY

Telechat

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

openvla

OpenVLA: An open-source vision-language-action model for robotic manipulation.

LIV

Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)

DecisionNCE

[ICML 2024] The offical Implementation of "DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning"

rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

rl_games

RL implementations

Eureka

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

MaxDiffRL

powerlevel10k

A Zsh theme

IsaacGymEnvs

Isaac Gym Reinforcement Learning Environments

CORL

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

rliable

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

LLM-Tuning

Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.

llama3

The official Meta Llama 3 GitHub site

DeepSpeedExamples

Example models using DeepSpeed

ReMax

Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)

open_clip

An open source implementation of CLIP.

RoboFlamingo

Code for RoboFlamingo

smac

SMAC: The StarCraft Multi-Agent Challenge

open_flamingo

An open-source framework for training large multimodal models.

phi2-finetune

Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

trl

Train transformer language models with reinforcement learning.

RVT

Official Code for RVT-2 and RVT

3d_diffuser_actor

Code for the paper "3D Diffuser Actor: Policy Diffusion with 3D Scene Representations"

calvin

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks