seanexp

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

atuin

✨ Magical shell history

Triton-Puzzles

Puzzles for learning Triton

lightning-thunder

Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

Sophia

The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

transformer-debugger

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

text-dedup

All-in-one text de-duplication

resource-stream

CUDA related news and material links

dynamax

State Space Models library in JAX

nanotron

Minimalistic large language model 3D-parallelism training

large-scale-lm-tutorials

Large-scale language modeling tutorials with PyTorch

unlikelihood_training

Neural Text Generation with Unlikelihood Training

weak-to-strong

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

how-engineering-communicates

A community version of the "common API" for how the GitHub Engineering organization communicates

ml-engineering

Machine Learning Engineering Open Book

the-art-of-command-line

Master the command line, in one page

awesome-design-patterns

A curated list of software and architecture related design patterns.

trl

Train transformer language models with reinforcement learning.

safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

text-embeddings-inference

A blazing fast inference solution for text embeddings models

Dromedary

Dromedary: towards helpful, ethical and reliable LLMs.

Lemur

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

spinningup

An educational resource to help anyone learn deep reinforcement learning.

rl

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

PPOCoder

Code for the TMLR 2023 paper "PPOCoder: Execution-based Code Generation using Deep Reinforcement Learning"

ColossalAI

Making large AI models cheaper, faster and more accessible

reflexion

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning