Metrics that matter in production for LLMs: a simple frameworkThe difference between a prototype and an actual applicationSep 17, 2024Sep 17, 2024
Ideas for thinking about LLM quality“Your question is not related to any of the datasets in my database. I am happy to help with questions related to sales and product…Aug 26, 2024Aug 26, 2024
What is a ComposerModel? Why is it useful for training neural networks?When I first started using the OSS libraries Composer and LLM Foundry for training Large Language Models, I was surprised to see an…Jul 31, 2024Jul 31, 2024
How MLflow Traces allows me to improve my NBA stats SQL Agent💻 code for this article is hereJul 24, 2024Jul 24, 2024
Trustworthy AI frameworks in Asia — analysing China and Singapore’s published guidance for…This article represents a personal opinion only.Jan 20, 2024Jan 20, 2024
A simple playbook for evaluating LLMs for your language-specific use casecode for this post can be found hereMay 30, 20232May 30, 20232
