A framework for federated fine-tuning of retrieval-augmented generation (RAG) systems.

A toolkit for evaluating and monitoring AI models in clinical settings

An mdbook preprocessor for the ai-pocket-reference project!

A flexible, modular, and easy to use library to facilitate federated learning research and development in healthcare settings

An AI-powered tool for bias detection and risk management, promoting sustainable and trustworthy AI systems.

Efficient LLM inference on Slurm clusters using vLLM.

A streamlined reference manual for AI practitioners, students, and developers to quickly look up core concepts and implementations.

Working with Jobboard API to perform actions needed by Vector Institute

VLDBench: A large-scale benchmark for evaluating Vision-Language Models (VLMs) and Large Language Models (LLMs) on multimodal disinformation detection.