个人构建MoE大模型：从预训练到DPO的完整实践

Implementation for FP8/INT8 Rollout for RL training without performence drop.

Automated tool for running Python programs in a streamlined manner

An Open-source RL System from ByteDance Seed and Tsinghua AIR

GTP engine and self-play learning in Go

Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.

A PyTorch implementation of DeepMind's AlphaZero agent to play Go and Gomoku board games

Minimal reproduction of DeepSeek R1-Zero

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

minimal-cost for training 0.5B R1-Zero

Democratizing Reinforcement Learning for LLMs

High Dimensional Integration with GPU

PyMatching: A Python/C++ library for decoding quantum error correcting codes with minimum-weight perfect matching.

Robust and fast Monte Carlo algorithm for high dimension integration

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Teaching Addition to Small Transformers

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

Awesome resources on normalizing flows.

Machine learning algorithms for many-body quantum systems

AllocCheck

Julia functional programming infrastructures and metaprogramming facilities

Toolbox for Green's functions on Matsubara grids

Create any job from Julia functions

A simple workflow engine powered by Julia

Express: a high-level, extensible workflow framework for accelerating ab initio calculations for the materials science community

phq: a Fortran code to compute phonon quasiparticle properties and dispersions

Interface and Julia implementation of exchange-correlation functionals

Julia bindings to the libxc library for exchange-correlation functionals