MLOps.community  cover image

Treating Prompt Engineering More Like Code // Maxime Beauchemin // MLOps Podcast #167

MLOps.community

CHAPTER

How to Fine Tune a Text to Sequel Challenge

The challenge is, what are there's a lot of private context here? And clearly that doesn't fit in a prompt. So then the other approach like, can we just fine tune a month? I create a corpus of 10,000 tables and throw my dbt pipelines into it. Then I'll fine tune a model that will have the full context of all my data catalog and more. But if you train a model with a bunch of information, so at OpenAI, they have this sequence of training and the SQL teaching portion of it.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner