Home Projects self-instruct
self-instruct
Python

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

by yizhongw · GitHub
Stars
Forks
License
Created
Last commit
Language
general-purpose-modelinstruction-tuninglanguage-modelApache-2.0Python
View on GitHub
In plain words

Improve language models' ability to follow instructions by generating their own training data.

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 →
self-instruct — GitHub preview card
📈 Star history
4 6114 606
2026-07-122026-08-31
📈 Track self-instruct

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

Aligning pretrained language models with instruction data generated by themselves.

self-instruct has 4.6k stars on GitHub. It has been forked 518 times. self-instruct is written mainly in Python. It has been in active development since 2022. self-instruct is available under the Apache-2.0 license. Its main topics are general-purpose-model, instruction-tuning, language-model.

Frequently asked questions

What is self-instruct?

Aligning pretrained language models with instruction data generated by themselves.

Is self-instruct open source?

self-instruct is an open-source project. It is released under the Apache-2.0 license.

Is self-instruct free?

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

What license does self-instruct use?

self-instruct is available under the Apache-2.0 license.

What language is self-instruct written in?

self-instruct is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — self-instruct

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

[![olud.ai](https://olud.ai/badge.php?tool=yizhongw-self-instruct)](https://olud.ai/project/yizhongw-self-instruct.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.