Home Projects RETRO-pytorch
RETRO-pytorch
Python

RETRO-pytorch

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

by lucidrains · GitHub
Stars
Forks
License
Created
Last commit
Language
artificial-intelligenceattention-mechanismdeep-learningApache-2.0Python
View on GitHub
In plain words

Build and test a retrieval-based AI model using Pytorch for improved attention mechanisms.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
RETRO-pytorch — GitHub preview card
📈 Star history
878877
2026-07-202026-08-31
📈 Track RETRO-pytorch

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

RETRO-pytorch has 877 stars on GitHub. It has been forked 109 times. RETRO-pytorch is written mainly in Python. It has been in active development since 2022. RETRO-pytorch is available under the Apache-2.0 license. Its main topics are artificial-intelligence, attention-mechanism, deep-learning, retrieval.

Frequently asked questions

What is RETRO-pytorch?

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

Is RETRO-pytorch open source?

RETRO-pytorch is an open-source project. It is released under the Apache-2.0 license.

Is RETRO-pytorch free?

Yes. RETRO-pytorch is free and open source — you can use, modify and self-host it.

What license does RETRO-pytorch use?

RETRO-pytorch is available under the Apache-2.0 license.

What language is RETRO-pytorch written in?

RETRO-pytorch is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — RETRO-pytorch

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=lucidrains-retro-pytorch)](https://olud.ai/project/lucidrains-retro-pytorch.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.