Now that we have the h2oGPT Large Language Model running locally on a desktop computer, let’s load it with our own data. I’ve gone on and on about how Large Language Models — so-called AIs — are crippled by training on bad data. Garbage In; Garbage Out! So let’s build a local LLM and feed it good data for a specific purpose. Welcome to Virtual Grad Student! We’re going to set up a Large Language Model to run locally, feed it a clean set of data, then make it available to authors as a virtual writer’s assistant. For example, to pull together a few paragraphs of background on Roman aqueduct architecture. Oh, and sorry again about the background!
Links:
The h2oGPT open source Large Language Model
Common Corpus, the largest public domain dataset for training LLMs
h2oGPT macOS, and Windows installers:
Easy Windows Installer for Windows 10 64-bit (CPU/CUDA)
Easy macOS Installer for macOS (CPU/M1/M2)
Next on Perfecting Equilibrium
Friday April 26th - Foto.Feola.Friday
Sunday April 28th — Highly Granular, Loosely Coupled Entropy is the strongest force in the universe. Without the Industrial Age benefits of economies of scale, the vast edifices that powered manufacturing economies like the United States will simply break down. Without those benefits, the bonds will simply fade. States will act more and more independently, and the Federal Government will have less ability to respond.
Loading your own data into your personal AI