// ⚙ Fine-tuning & PEFT

Prefix & Prompt Tuning

Learns only continuous soft-prompt vectors prepended to inputs.

前缀/提示微调 2021 Intermediate extended

IN PLAIN WORDS

Freeze the model and train a few vectors prepended to the input or each layer — a prompt only machines read. Larger models close the gap with full fine-tuning.

Used in: Serving many tasks on one base model

TIMELINE · prerequisites → this → what builds on it

2019 Adapters2021 Prefix & Prompt T…

01Original paper

The Power of Scale for Parameter-Efficient Prompt Tuning

Brian Lester, Rami Al-Rfou, Noah Constant · 2021

arXiv ↗ ✓ Verified · arXiv API

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

Adapters

Prefix & Prompt Tuning

Then you can learn

Nothing in the atlas builds on it yet

Related:LoRA (Low-Rank Adaptation)

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Official docs

huggingface.co ↗EN

04Where the course teaches it

U50 Instruction Tuning & PEFT SFT, synthetic data, LoRA/QLoRA/DoRA, adapters and model merging. 10 h8 algorithms3 paperslesson ready

For AI / data

Verification: verified, checked 2026-10-21.
JSON: /api/learn/algorithms.json (id: prompt-tuning)