The toolkit to test, validate, and evaluate your models and surface, curate, and prioritize the most valuable data for labeling.

NitroML is a modular, portable, and scalable model-quality benchmarking framework for Machine Learning and Automated Machine Learning (AutoML) pipelines.

Benchmarking the ability of large language models to detect semantic conflicts across domains, documents, and evolving knowledge bases.

Intro to Machine Learning Project from TripleTen

A model predicts whether a patient will be diagnosed with diabetes