Hugging Face PEFT Documentation
by Hugging Face
The reference for parameter-efficient fine-tuning: LoRA, QLoRA, and friends.
Overview
PEFT (Parameter-Efficient Fine-Tuning) is how most teams fine-tune large models without renting a datacenter. These docs explain and demonstrate LoRA, QLoRA, prefix tuning, and adapters, showing how to fine-tune billion-parameter models on a single GPU by training only a small set of extra weights. Conceptual guides plus copy-pasteable code make it the go-to reference once you're past your first fine-tune.
At a Glance
- Topic
- Fine-Tuning
- Level
- Advanced
- Format
- Documentation
- Cost
- Free
- Duration
- Self-paced
- Provider
- Hugging Face
- Hands-on
- Yes — code/exercises
- Certificate
- None
What You’ll Learn
- ✓LoRA and QLoRA for efficient fine-tuning
- ✓Adapters, prefix, and prompt tuning
- ✓Fine-tuning large models on a single GPU
- ✓Merging and serving adapters
Highlights
- •Reference for the dominant efficient-tuning methods
- •Runnable examples with the HF ecosystem
Who It’s For
Best For
- ✓Engineers fine-tuning large models on limited hardware
Prerequisites
- •Python
- •PyTorch and transformers basics
FAQ
What is Hugging Face PEFT Documentation?
Official docs and tutorials for Hugging Face PEFT, the library for parameter-efficient fine-tuning methods like LoRA and QLoRA.
Is Hugging Face PEFT Documentation free?
Hugging Face PEFT Documentation is free to access.
What level is Hugging Face PEFT Documentation for?
Hugging Face PEFT Documentation is aimed at a advanced audience. Recommended background: Python, PyTorch and transformers basics.
How long does Hugging Face PEFT Documentation take?
Expect roughly Self-paced. Most learners work through it at their own pace.
What will I learn from Hugging Face PEFT Documentation?
You'll learn: LoRA and QLoRA for efficient fine-tuning; Adapters, prefix, and prompt tuning; Fine-tuning large models on a single GPU; Merging and serving adapters.