Hey, everyone. As you all can probably tell, I'm not Andreea. So, fortunately or unfortunately for you, I will be helping you through this module.
Welcome to the fifth module where we'll go into building an LLM. And by building, I mean fine-tuning your own large language model. We'll learn how to host these.
You'll also learn how to host a local version of LLM that doesn't need to talk to the internet. The first video in the series will be by Rob, where he'll teach you how you can host H2O GPT locally and run the UI. Essentially, you'll have your own private GPT running on your system.
After which, I will help you learn how to fine-tune your own model using H2O LLM Studio, which is a fully open-source, no-code local tool for you to actually build your own GPT model. After that, I'll guide you a bit as to how you can proceed. After that, you'll get some homework, which will be to essentially build your own GPT model.
I'll give you some pointers, and there'll be some help that you might get. But I'm super excited to help you through this session. For the next module, here's Rob Miller teaching you all about a private GPT model.