← Back to Learning Hub

4.1 LLM Fundamentals

Beginner · 3 articles · MODULE 4: LLM ENGINEERING

Tokenization

Tutorial · Beginner · 21 min

A model never sees your text. It sees tokens: chunks of characters produced by a compression algorithm learned from training data.

TokensModels

Includes Colab notebook

By: Anacodic Team

Start Reading →

How LLMs Work

Tutorial · Beginner · 22 min

A language model does exactly one thing: given the tokens so far, output a probability for every possible next token.

How LLMs workTokens

By: Anacodic Team

Start Reading →

Sampling and Temperature

Tutorial · Beginner · 21 min

A model hands you a probability for every possible next token; sampling is the separate step that picks one, and it is not part of the model.

SamplingDecoding

Includes Colab notebook

By: Anacodic Team

Start Reading →