4
Vectors and embeddings
- Learned
Distinguish , , and learned .
Look inside language models, then build with Python
Steps 4–9 cover and , and , and verification, then building and evaluating small . Start after steps 1–3.
Where are you in the 9 steps?
- Beginner Use and check its answers
- Intermediate Look inside a
- Advanced Build and evaluate with
- Level 1 AI, machine learning, and language models
- Level 2 Write and check a prompt
- Level 3 Text, tokens, and IDs
- Level 4 Vectors and embeddings
- Level 5 Training, inference, and retrieval
- Level 6 Instructions, sampling, and verification
- Level 7 Python: run, inspect, change
- Level 8 Numbers, predictions, and activations
- Level 9 Train and evaluate a small model
How to study this course
- Press a step on the stairs to open its Course chapter. Read the goal first, then the body.
- Use the practice tool marked for that step in the table below. Doing it yourself stays with you much longer than only reading.
- 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-
-
5
Training, inference, and retrieval
- Training
Explain what changes in and what a uses at time.
-
6
Instructions, sampling, and verification
- Instructions
- Verification
Know that always giving the same answer (consistency) is not the same as giving a right answer (factual accuracy), and compare generation settings.
Advanced
Build and evaluate with Python
Small steps, real code-
7
Python: run, inspect, change
- Variables
- Conditions
- Functions
Use variables, conditions, and functions in the .
-
8
Numbers, predictions, and activations
- Input numbers
- Prediction
Build small functions such as mean and maximum, and explain what their outputs mean.
-
9
Train and evaluate a small model
- Split the
- Train
- Evaluate
Split into training and evaluation sets, and explain what a score cannot tell you.
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 |