llm

In this blog, we demonstrate how to rapidly run deep learning experiments for vision and multimodal AI using a Hydra-powered workflow. By leveraging PyTorch Lightning and W&B, we streamline training, logging, and batch processing of images with CLIP and LLM pipelines.

This blog explores the fundamentals and advancements of generative AI, including foundation models, prompt engineering, and Retrieval-Augmented Generation (RAG), highlighting their applications, frameworks, and practical implementations.

This blog explains how to build a Streamlit web app that generates multiple-choice questions (MCQs) from lecture content using a language model (LLM). It also demonstrates how to integrate these questions into a Google Quiz using the Forms API for automated quiz creation