An advanced module after the agentic practice: how LLMs are built and trained, why data is the main work, when to fine-tune and when a prompt and context are enough — and your own fine-tune of a small model on a free GPU

Duration: 42 min

Module goals

• Explain how tokens, embeddings, attention and pretraining on next-token prediction add up to an LLM — and why the same design produces confident mistakes
• Lay out your task along the machine learning cycle and pick an algorithm class by what you need to get — including the conclusion "no LLM needed here"
• Decide whether fine-tuning is needed or the task is closed by a prompt, context/RAG and agents; choose between full fine-tuning and LoRA and pick a small model
• Plan an honest evaluation: set the holdout aside before training, recognize overfitting and forgetting, tell a benchmark apart from a check on your own task
• Fine-tune a small model on a free GPU or your own hardware and record a "before / after / prompt without fine-tuning" comparison against criteria set in advance

Units

What's inside a model

Data is the main work

Fine-tuning: when and how

Evaluation: did it help

Practice: fine-tune a small model

The course is free — start on the site →

Write to the author: Telegram · LinkedIn

checked against the course: 2026-11-02 · 664b147