Home Projects llark
llark
Jupyter Notebook

llark

Code for the paper "LLark: A Multimodal Instruction-Following Language Model for Music" by Josh Gardner, Simon Durand, Daniel Stoller, and Rachel Bittner.

by spotify-research · GitHub
Stars
Forks
Created
Last commit
foundation-modelmultimodalmusic-information-retrievalJupyter Notebook
View on GitHub
In plain words

Explore and preprocess music datasets using code related to a multimodal music model.

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 →
llark — GitHub preview card
📈 Star history
383382
2026-07-202026-08-31
📈 Track llark

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

Code for the paper "LLark: A Multimodal Instruction-Following Language Model for Music" by Josh Gardner, Simon Durand, Daniel Stoller, and Rachel Bittner.

llark has 382 stars on GitHub. It has been forked 34 times. llark is written mainly in Jupyter Notebook. It has been in active development since 2023. Its main topics are foundation-model, multimodal, music-information-retrieval.

Frequently asked questions

What is llark?

Code for the paper "LLark: A Multimodal Instruction-Following Language Model for Music" by Josh Gardner, Simon Durand, Daniel Stoller, and Rachel Bittner.

Is llark open source?

llark is an open-source project.

Is llark free?

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

What language is llark written in?

llark is written mainly in Jupyter Notebook.

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

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

[![olud.ai](https://olud.ai/badge.php?tool=spotify-research-llark)](https://olud.ai/project/spotify-research-llark.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.