45 free lesson minutes · Start now, no credit card needed
Shiur Prati

Private Fine-Tuning & Open Models lessons with AI

Fine-Tuning & Open Models with a live private lesson: the teacher talks with you out loud and explains on a shared board, moving at your pace through a clear plan, lesson after lesson.

Live 1:1 lesson with an AI teacher

Teacher: Noa

  • Course updated 11/2026
  • Hebrew, and 5 more languages
  • 3 levels
  • 36 lessons · about 19 hours of lessons

Fine-Tuning & Open Models

Fine-Tuning & Open Models with a live private lesson: the teacher talks with you out loud and explains on a shared board, moving at your pace through a clear plan, lesson after lesson.

12 lessons · 3 modules · Live private lesson with the teacher on the board

What you'll learn

  • Inside an LLM and Open Models
  • When to Fine-Tune: Prompt, RAG, or Fine-Tuning
  • Preparing Data for Fine-Tuning
  • Why Full Fine-Tuning Is Expensive: Memory and PEFT
  • LoRA in Depth
  • Running Locally and Serving
  • Evaluating a Fine-Tuned Model
  • Beyond SFT: Preferences and Synthetic Data
  • Licences, Data and Regulation
  • Compute Costs and Production

What's included

  • Live 1:1 lessons with an AI tutor on a shared board
  • 19 hours of live one-on-one lessons
  • 36 lessons on a shared board, each with a clear goal
  • Practice and a understanding check in every lesson
  • A summary after every lesson, saved in the history
  • A completion certificate for each level
  • Computer, tablet or phone
  • Hebrew, plus 5 more languages

Course plan

3 levels · 10 modules · 36 lessons · 19 hr 20 min total

BeginnersBeginner: Open Models, When to Fine-Tune, and Data Preparation3 modules • 12 lessons • 6 hr 25 min
  1. Inside an LLM and Open Models4 lessons • 2 hr
    1. 1How an LLM Works: Tokens, Weights, PredictionTrial lessonabout 30 min
    2. 2From Base Model to Chat Model: Pretraining, SFT, RLHFabout 30 min
    3. 3Open vs Closed Modelsabout 30 min
    4. 4Reading a Model Card and Choosing an Open Modelabout 30 min
  2. When to Fine-Tune: Prompt, RAG, or Fine-Tuning4 lessons • 2 hr 10 min
    1. 5How Far a Prompt Can Take Youabout 30 min
    2. 6RAG: Giving the Model Knowledge at Query Timeabout 30 min
    3. 7The Decision Tree: Prompt, RAG, or Fine-Tuneabout 35 min
    4. 8What Fine-Tuning Actually Does: The Training Loopabout 35 min
  3. Preparing Data for Fine-Tuning4 lessons • 2 hr 15 min
    1. 9From Task to Dataset: Which Examples You Needabout 30 min
    2. 10Data Format: JSONL and Chat Templatesabout 30 min
    3. 11Cleaning, Privacy, and Splitting the Dataabout 35 min
    4. 12Project: A Full Fine-Tuning Plan for a Real Caseabout 40 min
IntermediateIntermediate: LoRA, Quantisation and Running Models Locally3 modules • 12 lessons • 6 hr 25 min
  1. Why Full Fine-Tuning Is Expensive: Memory and PEFT2 lessons • 1 hr
    1. 1Where GPU Memory Goes During Trainingabout 30 min
    2. 2The PEFT Family: Training Few Parametersabout 30 min
  2. LoRA in Depth6 lessons • 3 hr 10 min
    1. 3LoRA Math: Low-Rank Updatesabout 35 min
    2. 4LoRA Hyperparameters: Where and How Bigabout 30 min
    3. 5Quantisation Basics: From 16-bit to 4-bitabout 30 min
    4. 6QLoRA: Fine-Tuning a Big Model on One GPUabout 30 min
    5. 7A Real Training Run: Config and Reading the Lossabout 35 min
    6. 8After Training: Merging and Serving Multiple Adaptersabout 30 min
  3. Running Locally and Serving4 lessons • 2 hr 15 min
    1. 9Post-Training Quantisation Formats: GGUF, GPTQ, AWQabout 30 min
    2. 10Running Locally: Memory, KV Cache and Speedabout 35 min
    3. 11Inference Servers: vLLM and an OpenAI-Compatible APIabout 30 min
    4. 12Project: From Adapter to a Running Modelabout 40 min
AdvancedAdvanced (Professional): Evaluating, Licensing and Costing Fine-Tuned Models4 modules • 12 lessons • 6 hr 30 min
  1. Evaluating a Fine-Tuned Model4 lessons • 2 hr 5 min
    1. 1Evaluation Plan: Defining Successabout 30 min
    2. 2Automatic Metrics and LLM-as-Judgeabout 35 min
    3. 3Regressions: Forgetting, Overfitting and Safetyabout 30 min
    4. 4Error Analysis and Data Iterationabout 30 min
  2. Beyond SFT: Preferences and Synthetic Data2 lessons • 1 hr 5 min
    1. 5Preference Tuning: DPO and Friendsabout 35 min
    2. 6Synthetic Data and Distillationabout 30 min
  3. Licences, Data and Regulation2 lessons • 1 hr
    1. 7Open Model Licencesabout 30 min
    2. 8Data Rights, Privacy and Regulationabout 30 min
  4. Compute Costs and Production4 lessons • 2 hr 20 min
    1. 9Training Compute: FLOPs and GPU-Hoursabout 35 min
    2. 10Inference Cost: Self-Hosting vs APIabout 35 min
    3. 11Fine-Tuned Models in Production: Monitoring and Versioningabout 30 min
    4. 12Capstone: A Fine-Tuning Decision Dossierabout 40 min

What you need

  • No prior knowledge needed for beginner level: the teacher checks what you already know and starts from there
  • For higher levels: what you learned at the level before (you can skip it if you already know it)
  • A computer, tablet or phone with a microphone, and a browser

Who it's for

  • Adults: for work, study, an exam, or just curiosity
  • AI & Machine Learning

    with Noam

    Live 1:1 lesson with an AI teacherabout 19 hours35 lessons3 levels
  • Using AI Wisely

    with Noam

    Live 1:1 lesson with an AI teacherabout 12 hours24 lessons2 levels
  • Machine Learning

    with Noam

    Live 1:1 lesson with an AI teacherabout 20 hours36 lessons3 levels
  • Deep learning

    with Noa

    Live 1:1 lesson with an AI teacherabout 18 hours34 lessons3 levels
  • Computer Vision

    with Noam

    Live 1:1 lesson with an AI teacherabout 20 hours36 lessons3 levels
  • Generative AI & Prompt Engineering

    with Noa

    Live 1:1 lesson with an AI teacherabout 19 hours36 lessons3 levels
See all courses in Artificial Intelligence

Your teacher

NoaNoaAI private tutor, in a live lesson on a shared board

A private AI teacher who teaches in a live conversation: asks, listens, draws on the board, and lets you solve it yourself with hints. Remembers what you've learned and starts each lesson where you left off.

What's a lesson like?

  • Your child talks with the teacher out loud, like a video call, and asks about anything unclear.

  • The teacher explains, writes and draws on a shared board, and your child solves along on the same board.

  • Snap a photo of a worksheet or homework and work through it, one problem at a time.

  • Parents get a report: study time, what went well and what needs more practice.

Lesson rules

  • Just Learning

FAQ

How does a private Fine-Tuning & Open Models lesson work?
Pick Fine-Tuning & Open Models and a level, then talk with the teacher out loud. The teacher asks what you already know, explains, writes and draws on the board, and lets you solve on your own with hints until it's clear.
How long does the Fine-Tuning & Open Models course take?
12 lessons of about 32 minutes at the first level, at your own pace. You can pause, go back, or skip what you already know.
Do I need prior knowledge?
Not for beginner level. At the start of the first lesson the teacher checks what you already know and adjusts the level, and you can jump straight to an advanced level.
How do I start for free?
Sign in with Google or a code sent to your email, enter your child's name and grade, and the lesson starts right away. Every family gets 45 free lesson minutes in any subject, counted by actual lesson time, with no credit card. Then choose a paid plan and cancel anytime.
What device do I need?
Any computer, tablet or phone with a browser and a microphone. You can also install the site as an app on your home screen.

Want to try it?

Sign in, enter your child's name and grade, and the lesson begins. 45 free lesson minutes, no credit card.

Start for free

Shiur Prati with AI: what it is and how it works

Fine-Tuning & Open ModelsThe first 45 minutes are free

Private lessonStart free