Medical-Event-Data-Standard/MEDS-DEV

We should support evaluation-only mode for pre-trained models distributed with weights

Open

#204 aperta il 14 mar 2025

Vedi su GitHub
 (0 commenti) (1 reazione) (0 assegnatari)Python (9 fork)github user discovery
Experimental APIModelsUsability/Interfaceenhancementhelp wantedpriority:medium

Metriche repository

Star
 (39 star)
Metriche merge PR
 (Metriche PR in attesa)

Descrizione

Though this should not be the main focus of the benchmark, there is no reason it wouldn't work to just define a model with a predict step and no train step. This would be especially important as we add more of the stanford style models and the EHR Shot dataset (#203) which are more aligned with this approach.

Guida contributor