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:

Deepseek-Coder-33B-Base

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

Proprietary dataset. Includes GitHub (possibly without licensing filtering) and StackExchange.

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

Model available on HuggingFace.

https://huggingface.co/deepseek-ai/deepseek-coder-33b-base

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

Weights: Apache-2.0. Code: not released. Data: Apache-2.0 for end model, base model data not disclosed.

https://huggingface.co/senseable/33x-coder https://huggingface.co/datasets/andersonbcdefg/synthetic_retrieval_tasks https://huggingface.co/datasets/ise-uiuc/Magicoder-Evol-Instruct-110K

Last updated 30 April 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 12 June 2026, website content last updated 12 June 2026.