OkayStudy
EN English 한국어 日本語 中文 हिन्दी বাংলা اردو Español Português Français Deutsch Русский العربية Bahasa Indonesia Tiếng Việt ไทย Türkçe

How to enable notifications

Notifications are unavailable in this browser or on this address. Try a supported browser on the secure SONUB site.

If notifications are blocked, allow them in your browser settings.

  1. Open the site controls beside the address bar, or your browser’s site settings. Set Notifications for this site to Allow.
  2. In your device settings, allow notifications for your browser and check Do Not Disturb or Focus.
  3. Return to SONUB, reload the page, and use the bell to enable notifications.

On iPhone or iPad, add SONUB to your Home Screen, open it there, then allow notifications.
Curriculum steps 4–9

Look inside language models, then build with Python

Steps 4–9 cover vectors and embeddings, training and inference, sampling and verification, then building and evaluating small Python models. Start after steps 1–3.

See beginner steps 1–3 first
A learner reads an open book under a glowing lightbulb, answers a quiz card next to a stopwatch, then looks at a results sheet and follows a dotted arrow back to the book; a small staircase with a trophy stands in the background.

Where are you in the 9 steps?

Bar height = step order (not a measured score)
  • Beginner Use and check its answers
  • Intermediate Look inside a
  • Advanced Build and evaluate with
  1. Level 1 AI, machine learning, and language models
  2. Level 2 Write and check a prompt
  3. Level 3 Text, tokens, and IDs
  4. Level 4 Vectors and embeddings
  5. Level 5 Training, inference, and retrieval
  6. Level 6 Instructions, sampling, and verification
  7. Level 7 Python: run, inspect, change
  8. Level 8 Numbers, predictions, and activations
  9. Level 9 Train and evaluate a small model

How to study this course

  1. Press a step on the stairs to open its Course chapter. Read the goal first, then the body.
  2. Use the practice tool marked for that step in the table below. Doing it yourself stays with you much longer than only reading.
  3. When you can explain the chapter in your own words, take the same-numbered level of the AI knowledge exam.
Intermediate

Look inside a language model

Follow the examples at your own pace
  1. 4

    Vectors and embeddings

    3. Learned

    Distinguish , , and learned .

    AI Lab Learn
  2. 5

    Training, inference, and retrieval

    Explain what changes in and what a uses at time.

    Build Your Own Learn
  3. 6

    Instructions, sampling, and verification

    1. Instructions
    3. Verification

    Know that always giving the same answer (consistency) is not the same as giving a right answer (factual accuracy), and compare generation settings.

    Build Your Own Learn
Advanced

Build and evaluate with Python

Small steps, real code
  1. 7

    Python: run, inspect, change

    1. Variables
    2. Conditions
    3. Functions

    Use variables, conditions, and functions in the .

    Code lab Learn
  2. 8

    Numbers, predictions, and activations

    1. Input numbers
    3. Prediction

    Build small functions such as mean and maximum, and explain what their outputs mean.

    Code lab Learn
  3. 9

    Train and evaluate a small model

    1. Split the
    2. Train
    3. Evaluate

    Split into training and evaluation sets, and explain what a score cannot tell you.

    Code lab Learn

Where each step gets hands-on

Where each step gets hands-on
Step Lab Build Your Own lab
4. and Yes No No
5. , , and retrieval No Yes No
6. Instructions, , and verification No Yes No
7. : run, inspect, change No No Yes
8. Numbers, predictions, and activations No No Yes
9. Train and evaluate a small No No Yes

Next

AI Knowledge Exam Check yourself with the exams for steps 4–9 AI Internals Follow a request all the way to the model
Keep going

Choose a pending booking to cancel. Each cancellation requires confirmation.

Your :

Close