Blog

Building a Large Language Model from scratch, part 5

Fine-tuning the LLM for specific tasks, in a final look at Rauschka's guide to the inner workings of a GPT.

Building a Large Language Model from scratch, part 4

Let's actually train the foundational GPT model from Rauschka's how-to guide.

Building a Large Language Model from scratch, part 3

Putting the GPT architecture together in a continued walkthrough of Rauschka's how-to book.

Building a Large Language Model from scratch, part 2

Diving deeper into Sebastian Rauschka's unpacking of the self-attention mechanism, step by step.

Building a Large Language Model from scratch, part 1

Tackling Sebastian Raschka's hands-on guide to how GPT-like large language models actually work.

Habeas: fun with secret court orders and web services

Building a prototype service for secret court order accountability, partly as a refresher on Flask.

Counting chickens before they hatch

I took much longer than I expected to post part 3 of my MLflow series. Why?

Let's explore MLflow, part 3: applying MLflow

The full, end-to-end demo of a forecasting experimental workflow using MLFlow.

Let's explore MLflow, part 2: the demo problem

How easy is it to get started with MLflow locally? In the second part in a series, I define the demo project for testing.

Let's explore MLflow, part 1: initial setup

How easy is it to get started with MLflow locally? The first part in a series where I walk through the docs and use it for a demo project.