Training from scratch is expensive. Pre-trained models encode rich representations that transfer across tasks, the backbone of modern applied ML.
Linear Head Prediction
~15 min· Easy
Fine-tuning Head Gradient
~20 min· Medium
LoRA Trainable Parameter Count
~6 min· Intro
LoRA Forward Pass
~12 min· Easy
Toolformer Call Filter
~10 min· Easy
Sign in for the concept check
Optional multiple-choice questions on the ideas behind this section. Most useful after you have tried the coding problems above.