What foundational concepts do you have to study if you would like to understand Large Language Models?
A lot of the code we use to interact with LLMs (Large Language Models) is hidden behind several APIs — and that’s a superb thing.
But when you are like me, and need to grasp the ins and outs of those magical models, there’s still hope for you. Currently, other than the researchers working on developing and training recent LLMs, there’s mostly two varieties of people fidgeting with most of these models:
- Users, that interact via applications similar to ChatGPT or Gemini.
- Data scientists and developers that work with different libraries, similar to llangchain, llama-index and even using Gemini or OpenAI apis, that simplify the technique of constructing on top of those models.
The issue is — and you will have felt it — that there’s a fundamental knowledge in text mining and natural language processing that is totally hidden away in consumer products or APIs. And don’t take me incorrect — they’re great for developing cool use cases around these technologies. But, if you would like to a have deeper knowledge to construct complex use cases or manipulate LLMs a bit higher, you’ll need to ascertain the basics — particularly when the models behave as you…