Large Language Model Archives

Large Language Model-Based Solutions: How to Deliver Value with Cost-Effective Generative AI Applications by Shreyas Subramanian.

Shreyas holds a PhD in Aerospace Engineering from Purdue University and MS in Mechanical Engineering from Wright State University. He is the former Director of Research at Robust Analytics. Today he is Principal Data Scientist at Amazon Web Services.

Here is a good, very practical guide for those who seek to build and deploy cost-effective LLM-based solutions. From selecting a model, pre-and post-processing, prompt engineering, and fine tuning. Shreyas is certainly providing insights for optimizing inference and affordable architectures for typical applications. So today, generative AI value is found at the intersection of performance and cost. Howver organizations must optimize their infrastructure in order to reduce cloud costs.

Shreyas is certainly emphasizing the “biggest” model is not always the best. Model Selection and Foundation should be a wise, smaller approach provides developers to focus on domain-specific models. This requires less computational resources.

Feature Engineering Bookcamp by Sinan Ozdemir.

Feature Engineering Bookcamp by Sinan Özdemir

Sinan holds both a BA and MA in Pure Mathematics from Johns Hopkins University. His graduate work focused on algebraic geometry with applications to cybersecurity. He was Founder and CTO of Kylie.ai and Legion Analytics. Today Sinan is the Founder and CTO of LoopGenius. He is also a former Lecturer/Adjunct Professor, teaching graduate-level Business Analytics, Mathematics, and Computer Science.

Sinan is addressing a very critical, yet often overlooked stage of machine learning pipelines. A transformation of raw data into informative features will make or break your efforts. He is advocating the quality of the input data is the true measurement for any model’s performance.

He is presenting to readers six hands-on projects to upgrade your training data using feature engineering. This “Bookcamp” thereby prioritizes project-based curriculum over theory since structures the text is the true craft for data scientists. Instead of focusing on mathematical transformations, Sinan asks the reader to solve business problems, such as predicting flight delays.