It is important to document models that are used and released. Even models and code released openly are important to document thoroughly, in order to specify how to use the model, recommended and non-recommended use cases, potential harms, state or justify decisions made during training, and more. The following tools can help with documentation.
5 Model Documentation Resources
- Home /
- Foundation Model Resources /
- Model Documentation Resources
Model Documentation
Text 5
Speech 5
Vision 5
Ecosystem Cards
Ecosystem Graphs centralize information about models and their impact in the broader ecosystem.
Text Speech VisionFoundation Model Transparency Index
An index to measure the transparency of a foundation model with respect to its inputs, development, and downstream uses or policies.
Text Speech VisionModel Card Resources
A release of several resources surrounding model cards, including templates and tools for easy documentation creation, and how these are frequently used in practice.
Text Speech VisionModel Cards
A standard for reporting and documenting machine learning models, for promoting and easing transparent and open model development or reporting.
Text Speech VisionHugging Face ML Research Release Toolkit
A new researcher guide to releasing model or data resources, documenting the research and Hugging Face objects.
Text Speech Vision