October 2024 – Andrew Fairless, Ph.D.

What I Read: Visual Guide, Quantization

By Andrew Fairless on October 30, 2024August 3, 2024

https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-quantization A Visual Guide to Quantization, Demystifying the Compression of Large Language ModelsMaarten GrootendorstJul 22, 2024 “…I will introduce the field of quantization in the context of language modeling andContinue readingWhat I Read: Visual Guide, Quantization

What I Read: Generative AI Platform

By Andrew Fairless on October 29, 2024August 3, 2024

https://huyenchip.com//2024/07/25/genai-platform.html Building A Generative AI PlatformChip Huyen7/24/24 “This post outlines the common components of a generative AI platform, what they do, and how they are implemented.”

What I Read: History, Transformer

By Andrew Fairless on October 28, 2024July 22, 2024

Shaping the Future of AI from the History of TransformerStanford CS25: V4 I Hyung Won Chung of OpenAIStanford Online “I will provide a highly-opinionated view on the early history ofContinue readingWhat I Read: History, Transformer

What I Read: Kernel, Convolutional Representations

By Andrew Fairless on October 24, 2024July 22, 2024

https://logb-research.github.io/blog/2024/ckn Kernel Trick I – Deep Convolutional Representations in RKHSOussama Zekri, Ambroise OdonnatJuly 18, 2024 “…we focus on the Convolutional Kernel Network (CKN) architecture proposed in End-to-End Kernel Learning withContinue readingWhat I Read: Kernel, Convolutional Representations

What I Read: standard error

By Andrew Fairless on October 22, 2024July 22, 2024

http://www.stat.columbia.edu/~gelman/research/published/standarderror.pdf What is a standard error?Andrew Gelman7 September 2023 “In statistics, the standard error has a clear technical definition… In practice, though, challenges arise when we go beyond the simpleContinue readingWhat I Read: standard error

What I Read: LLM evaluation

By Andrew Fairless on October 21, 2024July 22, 2024

https://hamel.dev/blog/posts/evals Your AI Product Needs EvalsHow to construct domain-specific LLM evaluation systems.Hamel HusainMarch 29, 2024 “…I’ve seen many successful and unsuccessful approaches to building LLM products. I’ve found that unsuccessfulContinue readingWhat I Read: LLM evaluation

What I Read: Data Flywheels, LLM

By Andrew Fairless on October 17, 2024July 20, 2024

https://www.sh-reya.com/blog/ai-engineering-flywheel Data Flywheels for LLM ApplicationsShreya ShankarJul 1, 2024 “This diagram illustrates my (idealized) architecture of an LLM pipeline, from input processing through evaluation and logging. It showcases ideas I’llContinue readingWhat I Read: Data Flywheels, LLM

What I Read: Use-cases, inverted PCA

By Andrew Fairless on October 16, 2024July 14, 2024

https://www.youtube.com/watch?v=ZK3_T-UgKWM Use-cases for inverted PCA:probabl.Jul 11, 2024 “A lot of people know of PCA for it’s ability to reduce the dimensionality of a dataset. It can turn a wide datasetContinue readingWhat I Read: Use-cases, inverted PCA

What I Read: Improving Language Models, Practical Size

By Andrew Fairless on October 15, 2024July 14, 2024

https://amaarora.github.io/posts/2024-07-07%20Gemma.html Gemma 2, Improving Open Language Models at a Practical SizeAman AroraJuly 9, 2024 “…we take a deep dive into the architectural components of Gemma 2 such as Grouped QueryContinue readingWhat I Read: Improving Language Models, Practical Size

What I Read: Hidden Infinity, Preference Learning

By Andrew Fairless on October 10, 2024July 14, 2024

https://www.cs.princeton.edu/~smalladi/blog/2024/07/09/dpo-infinity The Hidden Infinity in Preference LearningSadhika MalladiJuly 09 2024 “I demonstrate from first principles how offline preference learning algorithms (e.g., SimPO) can benefit from length normalization, especially when trainingContinue readingWhat I Read: Hidden Infinity, Preference Learning

Month: October 2024