Randall DeFauw – Medium

Randall DeFauw

Randall DeFauw

The Data “Center of Excellence”

In my previous posts I’ve talked a lot about technical details of Generative AI. But I’ve been thinking recently about how generative AI…

Oct 1, 2023

Oct 1, 2023

Randall DeFauw

Fine-tuning Llama 2 on Trainium instances

Llama 2 is a powerful and popular large-language model (LLM) published by Meta. There’s a lot of interest in fine-tuning Llama 2 with…

Sep 19, 2023

Sep 19, 2023

Randall DeFauw

Using Python imports to inject more relevant context into code generation prompts

A recent research paper proposed a method for injecting more relevant context into code generation prompts for LLMs. In a nutshell, rather…

Sep 13, 2023

Sep 13, 2023

Randall DeFauw

Running the HELM benchmarks on Amazon EC2

The HELM testing suite is probably the most well-known framework for comparing LLM performance. Several folks have asked about how to use…

Jul 25, 2023

Jul 25, 2023

Randall DeFauw

Evaluating Large Language Models

One of the interesting things about building generative AI solutions is the impressive number of models you can pick from. If you want to…

Jul 18, 2023

Jul 18, 2023

Randall DeFauw

A shared responsibility model for generative AI

One of the more useful things that AWS published is the shared responsibility model for cloud computing. This model succinctly describes…

Jul 2, 2023

A shared responsibility model for generative AI

Jul 2, 2023

Randall DeFauw

Randall DeFauw

I am s Sr. Principal Solutions Architect at AWS. The opinions I express here are my own, and do not reflect the views of my employer.

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams