Fine-tuning Datasets with Synthetic Inputs

There are virtually unlimited ways to fine-tune LLMs to improve performance at specific tasks... but where do you get the data from? In this video, I demonstrate one way that you can fine-tune without much data to start with — and use what little data you have to reverse-engineer the inputs required! I show step-by-step how to take a small set of data (for my example I use 20 press releases I pulled from the internet), use LLMs to generate the missing inputs, run a real fine-tuning job, and play with the model to see how it behaves. The actual fine-tuning cost $0.35. Turns out, fine-tuning…