ChatMusician

by Multimodal Art Projection

About the model:

Model for understanding and creating music through text. Symbolic instead of diffusion model. Predominantly generates music in the style of Irish music.

Model type:

Audio

Model performance class:

Limited

Link to the model:

https://huggingface.co/m-a-p/ChatMusician

Base models:

Llama-2-7B

End model:

ChatMusician

End model license:

MIT License

About the organisation:

Open-source AI research community.

Link to the organisation:

https://m-a-p.ai/

Model release date:

April 2024

Availability

Base Model Data

No dataset information found.

End User Model Data

https://huggingface.co/datasets/m-a-p/MusicPile

Base Model Weights

Gated model on HuggingFace.

https://huggingface.co/meta-llama/Llama-2-7b

End User Model Weights

https://huggingface.co/m-a-p/ChatMusician

Training Code

https://github.com/hf-lin/ChatMusician

Documentation

Code Documentation

partially documented

https://github.com/hf-lin/ChatMusician

Hardware Architecture

Preprint

https://arxiv.org/abs/2402.16153

Paper

https://aclanthology.org/2024.findings-acl.373/

Modelcard

https://huggingface.co/m-a-p/ChatMusician

Datasheet

Access

Licenses

Weights: MIT. Code: MIT. Data: Creative Commons.

https://huggingface.co/m-a-p/ChatMusician https://github.com/hf-lin/ChatMusician https://huggingface.co/datasets/m-a-p/MusicPile

Is this information not up to date?

Contribute here ->

Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by BSTN. This version of the index generated 12 June 2026, website content last updated 12 June 2026.