Cameron R. Wolfe, Ph.D.inTowards Data ScienceA Practitioners Guide to Retrieval Augmented Generation (RAG)How basic techniques can be used to build powerful applications with LLMs…Mar 266Mar 266
Cameron R. Wolfe, Ph.D.inTowards Data ScienceThe Basics of AI-Powered (Vector) SearchHow the modern AI boom has completely revolutionized search applications…Mar 182Mar 182
Cameron R. Wolfe, Ph.D.inTowards Data ScienceExplaining ChatGPT to Anyone in <20 MinutesDistilling the core components of generative LLMs into an accessible framework…Mar 14Mar 14
Cameron R. Wolfe, Ph.D.inTowards Data ScienceEasily Train a Specialized LLM: PEFT, LoRA, QLoRA, LLaMA-Adapter, and MoreTraining a specialized LLM over your own data is easier than you think…Mar 91Mar 91
Cameron R. Wolfe, Ph.D.inTowards Data ScienceThe Story of RLHF: Origins, Motivations, Techniques, and Modern ApplicationsHow learning from human feedback revolutionized generative language models…Feb 29Feb 29
Cameron R. Wolfe, Ph.D.inTowards Data ScienceProximal Policy Optimization (PPO): The Key to LLM AlignmentModern policy gradient algorithms and their application to language models…Feb 151Feb 151
Cameron R. Wolfe, Ph.D.inTowards Data SciencePolicy Gradients: The Foundation of RLHFUnderstanding policy optimization and how it is used in reinforcement learningFeb 6Feb 6
Cameron R. Wolfe, Ph.D.inTowards Data ScienceBasics of Reinforcement Learning for LLMsUnderstanding the problem formulation and basic algorithms for RLJan 311Jan 311
Cameron R. Wolfe, Ph.D.inTowards Data ScienceRLAIF: Reinforcement Learning from AI FeedbackMaking alignment via RLHF more scalable by automating human feedback…Jan 231Jan 231
Cameron R. Wolfe, Ph.D.inTowards Data ScienceSupervised Fine-Tuning (SFT) with Large Language ModelsUnderstanding how SFT works from idea to a working implementation…Jan 163Jan 163