Large Language Models (LLMs)

As you’ve learned - Large Language Models, or LLMs, are models trained on huge amounts of data. They have large amounts of “parameters”, which we’ll get into later in the course. These parameters define how much a model can “learn”.

OpenAI, the company behind ChatGPT, trained their models on the internet.

We continue to train them every time we use them.

This is great for ChatGPT because it’s meant for general use. It needs to be able to learn as much as possible, so that it can respond to anything.

It can answer questions, write stories, translate languages - it seems to do everything.

But, not all models need to do all that. In fact, for some, if they do too much, they’re less useful.

That’s where Small Language Models come in.