peft/pr_3207/en/index.md

# PEFT

🤗 PEFT (Parameter-Efficient Fine-Tuning) is a library for efficiently adapting large pretrained models to various downstream applications without fine-tuning all of a model's parameters because it is prohibitively costly. PEFT methods only fine-tune a small number of (extra) model parameters - significantly decreasing computational and storage costs - while yielding performance comparable to a fully fine-tuned model. This makes it more accessible to train and store large language models (LLMs) on consumer hardware.

PEFT is integrated with the Transformers, Diffusers, and Accelerate libraries to provide a faster and easier way to load, train, and use large models for inference.

  
    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="quicktour"
      >Quicktour
      Start here if you're new to 🤗 PEFT to get an overview of the library's main features, and how to train a model with a PEFT method.
    
    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./task_guides/prompt_based_methods"
      >How-to guides
      Practical guides demonstrating how to apply various PEFT methods across different types of tasks like image classification, causal language modeling, automatic speech recognition, and more. Learn how to use 🤗 PEFT with the DeepSpeed and Fully Sharded Data Parallel scripts.
    
    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./conceptual_guides/adapter"
      >Conceptual guides
      Get a better theoretical understanding of how LoRA and various soft prompting methods help reduce the number of trainable parameters to make training more efficient.
   
    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./package_reference/config"
      >Reference
      Technical descriptions of how 🤗 PEFT classes and methods work.
    
  

<iframe
	src="https://stevhliu-peft-methods.hf.space"
	frameborder="0"
	width="850"
	height="620"
>