CodeGen

by Salesforce

About the model:

Autoregressive language model for code synthesis. Base model licensed under Apache 2.0.

Model type:

Code

Model performance class:

Full

Link to the model:

https://huggingface.co/Salesforce/codegen25-7b-instruct_P

Base models:

CodeGen25-7B-Multi-P

End model:

CodeGen25-7B-Instruct-P

End model license:

Unknown (research purposes only)

About the organisation:

Major AI research company.

Link to the organisation:

https://www.salesforceairesearch.com/

Model release date:

June 2023

Availability

Base Model Data

Starcoderdata mentioned in modelcard and some more mentioned in paper

https://huggingface.co/datasets/bigcode/starcoderdata

End User Model Data

no information found

Base Model Weights

https://huggingface.co/Salesforce/codegen25-7b-instruct_P/tree/main

End User Model Weights

https://huggingface.co/Salesforce/codegen25-7b-instruct_P/tree/main

Training Code

Documentation

Code Documentation

Hardware Architecture

Preprint

Preprint published on arXiv.

https://arxiv.org/pdf/2305.02309

Paper

Preprint reported to be published as a conference paper at ICLR 2023 but not found

Modelcard

Datasheet

Access

Licenses

Apache-2.0, an OSI-approved license.

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.