Gemma Model Benchmark Suite
An open-source toolkit designed to democratize LLM analysis and benchmarking with deep customization and minimal compute requirements.
Blog PostAn open-source toolkit designed to democratize LLM analysis and benchmarking with deep customization and minimal compute requirements.
Blog PostA multi-modal AI assistant developed in 22 hours at EPFL, capable of analyzing images using natural language voice commands.
A project focused on uncovering how language tied to criminal behavior evolves over time within Dark Web forums.
Blog PostA deep learning project to classify different stages of baldness using CNNs and pre-trained models like ResNet50 and VGG16.
A smart water-saving system that uses a two-phase machine learning approach to train users and optimize household water consumption.
An AI-powered system that optimizes traffic flow by using a Prolog knowledge base, A* search, and HMMs for traffic prediction.