AquilaCode

by Beijing Academy of Artificial Intelligence

About the model:

Bilingual (English-Chinese) language model.

Model type:

Code

Model performance class:

Full

Link to the model:

https://huggingface.co/BAAI/AquilaCode-multi

Base models:

Aquila-7B

End model:

AquilaCode-multi

End model license:

BAAI Aquila Model Licence Agreement

About the organisation:

Chinese non-profit AI lab.

Link to the organisation:

https://www.baai.ac.cn/en/

Model release date:

July 2023

Availability

Base Model Data

Paper thoroughly outlines pretraining data sources.

https://arxiv.org/pdf/2408.07410

End User Model Data

No data sources mentioned.

Base Model Weights

Weights available through HuggingFace.

https://huggingface.co/BAAI/Aquila-7B

End User Model Weights

Weights available through HuggingFace.

https://huggingface.co/BAAI/AquilaCode-multi

Training Code

No training code repository easily available.

Documentation

Code Documentation

Hardware Architecture

Only minimal architecture information available.

Preprint

No preprint available.

Paper

Modelcard

Model card does not go very in-depth, mainly providing information about inference and global model information.

Datasheet

Access

Licenses

BAAI Aquila Model Licence Agreement, not an OSI-approved license.

https://huggingface.co/BAAI/AquilaCode-multi/blob/main/BAAI%20Aquila%20Model%20License%20Agreement.pdf

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 09 April 2026, website content last updated 11 March 2026.