1 repo
Standardized interfaces for wrapping and testing various machine learning models against consistent evaluation criteria.
Distinguishing note: Focuses on the integration layer for testing arbitrary models rather than the agent-specific logic.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Model Benchmarking Interfaces. Refine with filters or upvote what's useful.
Test registered models against defined datasets and scorers by wrapping them in a prediction function and passing them to the evaluation interface.