Loading
A model card is a short standard document shipped with a model stating what it was trained on, how it was evaluated, its intended use and its known failures; a datasheet does the same for a dataset.
Mitchell and colleagues proposed model cards as documentation accompanying trained models, covering intended use, evaluation across conditions and demographic groups, and ethical considerations; Gebru and colleagues proposed datasheets recording a dataset's motivation, composition, collection process and recommended uses. The Hugging Face Hub makes both the expected README of any model or dataset repository. For a cancer model the card is where the research-only notice, the cohorts, the splits and the external validation results belong.
Shares Research use only (RUO), Software as a medical device (SaMD), Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Hugging Face Hub, Reproducibility and negative results, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Reproducibility and negative results, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Open weights, open code and gated models, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Reproducibility and negative results, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Open weights, open code and gated models, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Reproducibility and negative results, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Open weights, open code and gated models, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.