Evaluation & safety · Glossary term
What is Model Card?
A structured report describing a model's intended uses, evaluation conditions, performance characteristics, limitations, and relevant ethical or safety considerations.
Why does Model Card matter?
It gives downstream builders context for deciding whether reported evidence applies to their users and deployment conditions.
Model Card in practice
Document model version, training and evaluation scope, subgroup results, known failure modes, prohibited uses, and the date of each claim.
What is the common confusion about Model Card?
A model card communicates evidence and limitations; it is not a certification, warranty, system threat model, or substitute for deployment-specific evaluation.
Learn Model Card in the course
Lessons that name Model Card in a title or section
- Model, System, and Dataset Cards
Three documentation formats structure AI transparency. Model Cards (Mitchell et al. 2019) — nutrition labels for models: training data, quantitative disaggregated analyses, ethical considerations,…
Covered in Phase 18: Ethics, Safety & Alignment.
Related terms
- Eval SetA versioned collection of inputs, expected properties, scoring rules, and metadata used to measure an AI system against a defined…
- Dataset SplitA documented partition of examples into separate subsets for fitting, development decisions, and final evaluation.
- Distribution ShiftA difference between the data distribution used to build or evaluate a system and the distribution it encounters after deployment.
- AlignmentThe effort to make a model or AI system behave in ways that match intended goals, constraints, and human preferences across both expected…
- Datasheet for DatasetsStructured documentation of a dataset's motivation, composition, collection process, preprocessing, uses, distribution, maintenance, and…
Sources
More terms in Evaluation & safety
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.