PEFT

Hugging Face library for parameter-efficient fine-tuning

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

About

PEFT is the Hugging Face library for parameter-efficient fine-tuning of large pretrained models. It implements LoRA, prefix tuning, prompt tuning, P-tuning, IA3, adapter-based methods, and several newer techniques behind a small wrapper API that integrates with Transformers, Diffusers, and Accelerate. The library lets users adapt a model to a new task while training only a small fraction of its parameters. Apache 2.0 licensed.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Intermediate (3/5)
License
Apache-2.0
Minimum VRAM
8 GB
Added
Jan 29, 2026

Related Tools

Featured

Fine-tune LLMs 2x faster with 80% less memory

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Featured

Tool for fine-tuning LLMs with various configurations

Open SourceSelf HostedOfflineGPU 16GB+
Advanced
0.0 (0)

Open source data labeling platform for ML projects

Open SourceSelf HostedOffline
Easy
0.0 (0)
Featured

Library for accessing and sharing ML datasets

Open SourceSelf HostedOffline
Easy
0.0 (0)
Browse all Datasets & Training tools