Make with MakerSuite Part 2: Tuning LLMs- Google Developers Blog

What this post added

This post introduces Parameter Efficient Tuning (PET) within MakerSuite, a technique that allows developers to customize Large Language Models (LLMs) with hundreds of data points in minutes. It contrasts PET with traditional fine-tuning, highlighting PET's reduced complexity, data requirements, and computational cost. The post details the workflow for tuning models in MakerSuite, including creating a tuned model, selecting data (from saved prompts, Google Sheets, or CSV), viewing tuning progress, and running the newly tuned model.