peft

by huggingface · Machine Learning

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

New0 ratings21,636 starsActive
Machine LearningAI ApplicationPythonMakefile
Open project ↗↓ Download v0.20.0GitHub⚑ Report
peft preview

About this project

🤗 PEFT State-of-the-art Parameter-Efficient Fine-Tuning (PEFT) methods Fine-tuning large pretrained models is often prohibitively costly due to their scale. Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of large pretrained models to various downstream applications by only fine-tuning a small number of (extra) model parameters instead of all the model's parameters. This significantly decreases the computational and storage costs. Recent state-of-the-art PEFT techniques achieve performance comparable to fully fine-tuned models. PEFT is integrated with Transformers for easy model training and inference, Diffusers for conveniently managing different…

Technologies

PythonC++DockerfileMakefileCudadiffusionadapterfine-tuning

Project health

Actively maintained
Last update4 days ago
Contributors342
Latest releasev0.20.0
Open issues & PRs89
LicenseApache-2.0
On GitHubsince 2022

GitHub

21,636
stars
2,485
forks
342
contributors
89
open issues & PRs
Python
language
4 days ago
last commit
View on GitHub ↗All releases ↗

Reviews

out of 5 · 0 ratings
★★★★★
0%
★★★★
0%
★★★
0%
★★
0%
0%
Sign in to write a review
No reviews yet
Be the first to review peft.

Built by

huggingface
Imported from GitHub · not yet claimed on GitPalace
View developer pageSign in with GitHub to claim

Maintain huggingface/peft? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like