The simplest, fastest repository for training/finetuning medium-sized GPTs.

Grandmaster-Level Chess Without Search

ForgER algorithm

Simple single-file baselines for Q-Learning in pure-GPU setting

A free and strong UCI chess engine

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Official Implementation for "The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing"

Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

This code accompanies the paper "Scalable Multi-Agent Model-Based Reinforcement Learning".

A new markup-based typesetting system that is powerful and easy to learn.

A repository for training nanogpt-based Chess playing language models.

A repo to evaluate various LLM's chess playing abilities.

A scheduler for GPU/CPU tasks

Official Implementation for "HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach"

Fast and customizable framework for automatic and quick Causal Inference in Python

Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024

Optimal any-angle planner for a single agent in environments with dynamic obstacles

(Crafter + NetHack) in JAX. ICML 2024 Spotlight.

[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.

BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.

[AAAI-2024] Follower: This study addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed Follower approach utilizes a combination of a planning algorithm f…

A neural network training framework within a task-based parallel programming paradigm