Skill · Applied AI · Understand, serve and integrate language models
Explain how an LLM works, its inference and its quantization
Explain how an LLM works: Transformer and attention, tokenization, inference phases and KV cache, quantization and the size versus quality trade-off.
Start lesson 1The Applied AI domain
- 4 lessons
- ~2 h 20 of reading
- 4 quizzes
- 0 proof lab
The path
Where it comes from, where it leads
What you need to know first, where you stand on this skill, and what it opens next. Your status is computed in your browser, from what you have read and passed.
Before · no prerequisite
A foundation skill: you can start right away.
This skill, for you
Explain how an LLM works, its inference and its quantization
Computing
It unlocks · nothing yet
No other skill requires it: it is an end-of-path skill.
The path through the foundations From the most upstream foundation to this skill: what is in place, what remains to read.
Lessons
How to learn it
4 lessons, about ~2 h 20, in program order. Each lesson ends with its quiz.
The program
4 lessons · ~2 h 20
Part 1 · Fondamentaux (in French) 1 lesson · ~35 min
- 1Anatomie d'un LLM (in French)· 35 min
Part 2 · Inférence (in French) 3 lessons · ~1 h 45
Beyond the lessons
Assess, practise, pass the proof
Reading a lesson confirms nothing. A skill is confirmed by a passed quiz, practised in a guided lab, and put to the test by a challenge or a mission; an imported lab result is not verified by the site.
Assess yourself
4 quizzes
At the end of the lessons: passed at 70%, they confirm the skill.
Practice
No guided lab
No guided lab practices it yet.
Proof
No proof
Neither a challenge nor a mission with a proof yet.
Going further
Reference pages: they support the skill without teaching it, and do not count in your journey.
Placement test
Preparing the questions…
Your answers in detail
For each question asked: your answer, the correct answer, its explanation and the page to reread.
Around it
Who requires it, who teaches it
Required by
Taught by
Same block · Understand, serve and integrate language models