Introduction to LLMs
A beginner-friendly course covering the fundamentals of Large Language Models — what they are, how they work, and how to use them effectively.
By Admin
Free courseView course
Foundations · Beginner
How modern AI works
Tokens, embeddings, attention and scaling: the mechanics underneath every current model.
Why it matters
Every frontier technique is a variation on a few ideas. Knowing them lets you read new releases critically instead of taking claims on trust.
Key ideas
- Tokens and next-token prediction
- Embeddings
- Self-attention and the transformer
- Pre-training and scaling laws
- Context windows
You will be able to
- Explain how an LLM produces text
- Estimate cost from token counts
- Read a model card
Primary reading
- Attention Is All You Need (opens in a new tab)Vaswani et al. · 2017
- Scaling Laws for Neural Language Models (opens in a new tab)Kaplan et al. · 2020
- Training Compute-Optimal Large Language Models (opens in a new tab)Hoffmann et al. · 2022