maciek-pioro

ohmyzsh

🙃 A delightful community-driven (with 2,300+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python, etc), 140+ themes to spice up your morning, and an auto-update tool so that makes it easy to keep up with the latest updates from the community.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

triton

Development repository for the Triton language and compiler

LookaheadDecoding

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

WebLaTex

A complete alternative for Overleaf with VSCode + Web + Git Integration + Copilot + Grammar & Spell Checker + Live Collaboration Support. Based on GitHub Codespace and Dev container.

Triton-Puzzles

Puzzles for learning Triton

SAELens

Training Sparse Autoencoders on Language Models

MO-Gymnasium

Multi-objective Gymnasium environments for reinforcement learning

scattermoe

Triton-based implementation of Sparse Mixture of Experts.

transformer-physx

Transformers for modeling physical systems

scaling

Language models scale reliably with over-training and on downstream tasks

llm.scala

Extensible implementation of a Language Model (LLM) training framework in Scala.

ptdeco

ptdeco is a library for model optimization by decomposition built on top of PyTorch

sample-factory

High throughput synchronous and asynchronous reinforcement learning

neptune-client-experimental

how-to-use-plgrid

publications_2024

IDEAS scientific achievements

Megatron-LM

Ongoing research training transformer models at scale

MichalZawalski.github.io

mtyrolski.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

autoascend

The first place solution for the NeurIPS 2021 Nethack Challenge -- https://www.aicrowd.com/challenges/neurips-2021-the-nethack-challenge

fast_inference

llm_debate

Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"

minihack

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

nle-dashboard

sample-pretrain

emiliawisnios.github.io

llm_pipeline

mamba