Home Projects deita
deita
Python

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

by hkust-nlp · GitHub
Stars
Forks
Trending
License
Created
Last commit
Category
Language
alignmentdata-centricinstruction-tuningApache-2.0Python
View on GitHub
In plain words

Select and tune data for training large language models to improve their performance on specific tasks.

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 →
deita — GitHub preview card
📈 Star history
602599
2026-07-202026-08-31
📈 Track deita

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

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

deita has 602 stars on GitHub. It has been forked 33 times. deita is written mainly in Python. It has been in active development since 2023. deita is available under the Apache-2.0 license. Its main topics are alignment, data-centric, instruction-tuning, large-language-models.

Frequently asked questions

What is deita?

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

Is deita open source?

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

Is deita free?

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

What license does deita use?

deita is available under the Apache-2.0 license.

What language is deita written in?

deita is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — deita

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

[![olud.ai](https://olud.ai/badge.php?tool=hkust-nlp-deita)](https://olud.ai/project/hkust-nlp-deita.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.