LLM and Retrieval Fundamentals: sections and modules
T2.1Partly ready
How LLMs behave, for engineers
Explain tokens, context, sampling, embeddings and their cost effects.
About 3 h 1 min: 16 min reading + 2 h 45 min practice · 3 lessons
- Scope
- Behaviour, not training math
- Prerequisites
Lessons
Start moduleAlso used in this module
Lessons taught in another module that this one builds on.
- The Eight Cost and Latency Drivers
7 min · Credited source
Practise and Check
- Deliverable
- Token and cost estimator exercise
- Assessment
- Checkpoint
- Interview probe
- Why did the model ignore part of the prompt?
- Common mistakes
- Treating context as free
- Temperature myths
Your Progress
Saved in this browser when you leave the box.