33x-Coder

by Common Sense

About the model:

Pre-CodeLlama coder model

Model type:

Code

Model performance class:

Limited

Link to the model:

https://huggingface.co/senseable/33x-coder

Base models:

Llama-2-34B

End model:

33x-Coder

End model license:

Apache-2.0

About the organisation:

Common Sense, a collective of LLM developers

Link to the organisation:

https://huggingface.co/senseable

Model release date:

January 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

Two data sources linked, however unclear if they are the only ones used.

https://huggingface.co/datasets/andersonbcdefg/synthetic_retrieval_tasks https://huggingface.co/datasets/ise-uiuc/Magicoder-Evol-Instruct-110K

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

Weights made available on HuggingFace.

https://huggingface.co/senseable/33x-coder

Training Code

No repo containing training code found.

Documentation

Code Documentation

No training code, so undocumented.

Hardware Architecture

No hardware architecture documented.

Preprint

No preprint found.

Paper

No peer-reviewed paper found.

Modelcard

Model card provides only surface-level detail.

https://huggingface.co/senseable/33x-coder

Datasheet

No datasheet found.

Access

Licenses

Apache-2.0, an OSI-approved license.

https://huggingface.co/senseable/33x-coder

Last updated 13 March 2026

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.