👉 Start building your dataset at www.entrypointai.com

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 can be pretty affordable!

Creating a dataset is half art and half science, but there is nothing particularly hard about it once you understand the core concepts.

You don't need an ML degree to build your own fine-tuning dataset and train a custom LLM. You just need to be able to think critically about what you want the model to do and how you want to steer the model through inputs.

Follow along as I share my thought process and tools to create fine-tuning datasets and see how decisions along the way affect our interaction with the model and its outputs.

Remember to press subscribe! ✅

You can try fine-tuning for yourself at:
https://www.entrypointai.com

My LinkedIn:
  / markhennings  

Entry Point AI Discord:
  / discord