Highlights
- Pro
Stars
A simple reference implementation of the single-worker MuLoCo optimizer in Jax & PyTorch. MuLoCo-1 has been shown to outperfrom Muon and have larger critical batch sizes.
Post-training with Tinker
Automatically generating mathematical questions through a multi-agent system that the original LLM cannot solve.
GFlowNet library specialized for graph & molecular data
📋 A list of open LLMs available for commercial use.
An offline deep reinforcement learning library
A playbook for systematically maximizing the performance of deep learning models.
Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch
A modular, easy to extend GFlowNet library
Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch
This repository contains code for the paper "Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning". https://arxiv.org/abs/2210…
A curated list of resources about generative flow networks (GFlowNets).
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
A collection of meta-learning algorithms in Jax
Rainbow: Combining Improvements in Deep Reinforcement Learning
Official release of CompoSuite, a compositional RL benchmark
A PyTorch implementation of Perceiver, Perceiver IO and Perceiver AR with PyTorch Lightning scripts for distributed training
BabyAI platform. A testbed for training agents to understand and execute language commands.
Change Python code while it's running without losing state
GPU Accelerated t-SNE for CUDA with Python bindings
A suite of test scenarios for multi-agent reinforcement learning.
Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"