AI360Xpert
Learning Paths
Learning path

LLM Foundations

A guided route from raw text to a working mental model of how large language models are trained and used.

  1. Understand tokenization and embeddings
  2. Learn self-attention and the transformer block
  3. See how models are pretrained and fine-tuned
  4. Ground answers with retrieval (RAG)
  5. Practice with interview questions

Who this is for

You know some Python and a little ML, and you want a clear order to learn how modern LLMs work — without jumping randomly between blog posts.

How to use this path

Work top to bottom. Each step builds on the last: you can't reason about RAG until attention clicks, and attention is easier once tokenization makes sense. Spend real time on step 2 — it's the keystone.

What you'll be able to do

By the end you'll be able to explain, in plain language, how a prompt becomes a prediction, why context windows matter, and when to reach for retrieval versus fine-tuning.