CodeLlama

by Meta

About the model:

Coder model by Meta.

Model type:

Code

Model performance class:

Full

Link to the model:

https://huggingface.co/meta-llama/CodeLlama-70b-Instruct-hf

Base models:

Llama-2-70B

End model:

CodeLlama-70B-Instruct

End model license:

Llama 2 Community License Agreement

About the organisation:

Meta, a major technology company.

Link to the organisation:

https://ai.meta.com/

Model release date:

March 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

Proprietary dataset used.

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

Gated model available on HuggingFace.

https://huggingface.co/meta-llama/CodeLlama-70b-Instruct-hf

Training Code

Repo exists, but does not contain training code.

https://github.com/meta-llama/codellama

Documentation

Code Documentation

No training code, so undocumented.

Hardware Architecture

Hardware architecture discussed in aggregate and with a low level of detail in the model's paper.

https://arxiv.org/pdf/2308.12950

Preprint

Preprint available through arXiv.

https://arxiv.org/pdf/2308.12950

Paper

No peer-reviewed paper found. Preprint presented as keynote in ICSE24.

https://conf.researchr.org/details/icse-2024/llm4code-2024-papers/2/Code-Llama-Open-Foundation-Models-for-Code

Modelcard

Model card provides some information about training and inference, however mostly contains usage instructions.

https://huggingface.co/meta-llama/CodeLlama-70b-Instruct-hf

Datasheet

No datasheet found.

Access

Licenses

Llama 2 Community License Agreement, not an OSI-approved license.

https://huggingface.co/meta-llama/CodeLlama-70b-Instruct-hf#model-details

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.