BTLM

by Cerebras

About the model:

Bittensor language model.

Model type:

Text

Model performance class:

Full

Link to the model:

https://huggingface.co/cerebras/btlm-3b-8k-chat

Base models:

BTLM-3B-8K-Base

End model:

BTLM-3B-8K-Chat

End model license:

Apache-2.0

About the organisation:

Manufacturer of large AI systems.

Link to the organisation:

https://huggingface.co/cerebras

Model release date:

December 2023

Availability

Base Model Data

Dataset taken down.

https://huggingface.co/datasets/cerebras/SlimPajama-627B

End User Model Data

Anthropic-HH-RLHF

https://huggingface.co/datasets/Anthropic/hh-rlhf

Base Model Weights

https://huggingface.co/cerebras/btlm-3b-8k-base

End User Model Weights

https://huggingface.co/cerebras/btlm-3b-8k-chat

Training Code

Documentation

Code Documentation

Hardware Architecture

Hardware architecture outlined in preprint

https://arxiv.org/pdf/2309.11568

Preprint

Preprint published on arXiv.

https://arxiv.org/pdf/2309.11568

Paper

Modelcard

https://huggingface.co/cerebras/btlm-3b-8k-chat

Datasheet

available for tuning data

https://huggingface.co/datasets/Anthropic/hh-rlhf

Access

Licenses

Weights: Apache-2.0. Code: not released. Data: Apache-2.0, MIT.

https://huggingface.co/cerebras/btlm-3b-8k-chat https://huggingface.co/datasets/Anthropic/hh-rlhf https://huggingface.co/datasets/cerebras/SlimPajama-627B

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.