Starling

by NexusFlow

About the model:

Open language model trained through RLAIF.

Model type:

Text

Model performance class:

Full

Link to the model:

https://huggingface.co/Nexusflow/Starling-LM-7B-beta

Base models:

Llama-2-13B

End model:

Starling-LM-7B-Beta

End model license:

Apache-2.0

About the organisation:

Company developing GenAI agents for enterprise workflows.

Link to the organisation:

https://huggingface.co/Nexusflow

Model release date:

May 2024

Availability

Base Model Data

Data nowhere disclosed or documented, and described only in the vaguest terms in a corporate preprint released by Meta.

https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/

End User Model Data

https://huggingface.co/datasets/berkeley-nest/Nectar

Base Model Weights

Download only after requesting access; requires signing a consent form

https://ai.meta.com/resources/models-and-libraries/llama-downloads/

End User Model Weights

https://huggingface.co/Nexusflow/Starling-LM-7B-beta

Training Code

https://huggingface.co/Nexusflow/Starling-LM-7B-beta

Documentation

Code Documentation

Hardware Architecture

Preprint

linked preprint not by model creators

Paper

Modelcard

https://huggingface.co/Nexusflow/Starling-LM-7B-beta

Datasheet

No datasheet found.

Access

Licenses

weights as apache2

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.