huggingface/peft

A well-kept workshop manual: a hugging-face nameplate, one plain sentence of purpose, a green-ruled tip card, and then the code is already on the bench.

github.com/huggingface/pefthuggingface/peft
Screenshot of https://github.com/huggingface/peft, © the authors. Shown for reference. Request removal
Venue
EMNLP 2025
Year
2025
First author
Zeju Qiu
Field
parameter-efficient finetuning
Template
Centred h1 '🤗 PEFT' and centred h3 tagline, two prose paragraphs and a GitHub [!TIP] alert; no badges, no images
Theme
Light + dark

Checked against the rendered page. The listed paper (Orthogonal Finetuning Made Scalable, EMNLP 2025, Zeju Qiu) is not mentioned in the README; the README cites the PEFT library itself (Mangrulkar et al., 2022), so the entry describes a library README, not a paper README. The README has no badges, so the Badges table records GitHub's alert and link colors instead.

Why it is here

As a library README it leads with a one-line purpose, a Tip callout and runnable quickstart code, then backs the value claim with memory and accuracy tables, which is a different, code-first style worth studying.

Overview

Header Block

Badge Colors

Section Outline

Guidelines

More like this