8
Fine-Tuning OpenAI GPT Models
Chapter 7, The Generative AI Revolution with ChatGPT, took us into the world of GPT assistants and APIs. We examined the Generative AI transformer, general-purpose technology through interactions and code. If all the technology we explored is so effective, why bother? Why not just use the ready-made solutions and forget about learning, preparing data, configuring parameters, and writing documentation?
The answer is quite simple. What can we do when a general-purpose model such as GPT-3 or GPT-4 doesn’t reach the accuracy threshold we need for our project? We have to do something. But what? In this chapter, we will explore fine-tuning to make sense of the choices we can make for a project to go in this direction ...
Get Transformers for Natural Language Processing and Computer Vision - Third Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
