huggingface/peft

Project overview

This project enables adaptation of large pretrained models by fine-tuning only a small fraction of extra parameters, reducing computational and storage costs while maintaining performance comparable to fully fine-tuned models. It is designed for AI engineers and developers who need to customize large models without the prohibitive expense of full parameter training.

Project type

Model Development · Infrastructure

Deployment

Refer to project documentation

License

Apache-2.0

Best for

• AI engineers, developers, and data teams who need to adapt large pretrained text or image models while minimizing computational and storage overhead.

Key capabilities

• Configure models for parameter-efficient fine-tuning using methods like LoRA by wrapping a base model with get_peft_model to train a tiny fraction of parameters.
• Load and run inference on a base model with a PEFT adapter applied using PeftModel.
• Creates model checkpoints that are only a few MBs in size instead of GBs.
• Combines PEFT methods with quantization to make it easier to train and load LLMs for inference.

Limitations and risks

• The Transformers integration does not include all functionalities offered in PEFT, such as methods for merging the adapter into the base model.

Getting started

• Install the library easily via pip and wrap a target pretrained model with get_peft_model in Python to begin training.

Evidence and sources

• README: Fine-tuning large pretrained models is often prohibitively costly due to their scale. Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of large pretraine…
• README: Install PEFT from pip: ```bash pip install peft ``` Prepare a model for training with a PEFT method such as LoRA by wrapping the base model and PEFT configuration with `get_peft_m…
• README: To load a PEFT model for inference: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel
• README: In many cases, you're only finetuning a very small fraction of a model's parameters and each checkpoint is only a few MBs in size (instead of GBs).
• README: Quantization is another method for reducing the memory requirements of a model by representing the data in a lower precision. It can be combined with PEFT methods to make it even…

Reviewed at: 2026-07-17T22:28:53Z