MDSection 23 of 38 · 6 subtopics
Fine-Tuning
Adapt pretrained models to specific tasks. SFT, instruction tuning, catastrophic forgetting, PEFT.
Learning path
Work through each subtopic in order. Click any file below to open its lesson. Track your progress with the checkbox at the bottom.
Subtopics
Each subtopic includes a concise explanation, code examples, and references.
01
Fine-Tuning
Base model → fine-tuned model pipeline.
fine-tuning
02
Pretraining vs Fine-Tuning
Side-by-side training comparison.
pretraining-vs-fine-tuning
03
Supervised Fine-Tuning
Instruction/response dataset.
supervised-fine-tuning
04
Instruction Tuning
Instruction-following playground.
instruction-tuning
05
Catastrophic Forgetting
Capability radar/chart.
catastrophic-forgetting
06
PEFT
Frozen vs trainable parameter map.
peft