Samuel FlenderinTowards Data ScienceLoRA: Revolutionizing Large Language Model Adaptation without Fine-TuningExploiting the low-rank nature of weight updates during fine-tuning results in orders of magnitude reduction in learnable parameters·8 min read·Apr 23, 2024--1--1
Samuel FlenderinTowards Data ScienceDemystifying Mixtral of ExpertsMistral AI’s open-source Mixtral 8x7B model made a lot of waves — here’s what’s under the hood·8 min read·Mar 17, 2024--4--4
Samuel FlenderinTowards Data ScienceThe Rise of Sparse Mixtures of Experts: Switch TransformersA deep-dive into the technology that paved the way for the most capable LLMs in the industry today·8 min read·Feb 15, 2024--1--1
Samuel FlenderinTowards Data SciencePushing the Limits of the Two-Tower ModelWhere the assumptions behind the two-tower model architecture break — and how to go beyond·8 min read·Dec 10, 2023--3--3
Samuel FlenderinTowards Data ScienceTowards Understanding the Mixtures of Experts ModelNew research reveals what happens under the hood when we train MoE models·8 min read·Nov 14, 2023----
Samuel FlenderinTowards Data ScienceThe Rise of Two-Tower Models in Recommender SystemsA deep-dive into the latest technology used to debias ranking models·7 min read·Oct 29, 2023--3--3
Samuel FlenderinTowards Data ScienceThe Multi-Task Optimization ControversyDo we need special algorithms to train models on multiple tasks at the same time?·6 min read·Sep 29, 2023--1--1
Samuel FlenderinTowards Data ScienceMachine Learning with Expert Models: A PrimerHow a decades-old idea enables training outrageously large neural networks today·9 min read·Sep 5, 2023--2--2
Samuel FlenderinTowards Data ScienceMulti-Task Learning in Recommender Systems: A PrimerThe science and engineering behind algorithms that try to do it all·8 min read·Jul 25, 2023----
Samuel FlenderinTowards Data ScienceDeep Learning in Recommender Systems: A PrimerA tour of the most important technological breakthroughs behind modern industrial recommender systems·9 min read·Jun 26, 2023--1--1