Peft Fine Tuning

This is HuggingFace's official library for fine-tuning large language models without breaking the bank on GPU memory. Instead of training all 8 billion parameters, LoRA trains less than 1% by inserting small adapter layers, letting you fine-tune a Llama 3.1 8B on a single consumer GPU. The QLoRA variant adds 4-bit quantization so you can actually fine-tune 70B models on 24GB of VRAM. The skill covers the full workflow from configuration to multi-adapter serving, where you can swap between task-specific adapters at runtime. If you're doing any serious LLM fine-tuning and don't have a datacenter budget, this is the standard approach.

skills.sh installs: 1.1K
GitHub stars: 14.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add orchestra-research/ai-research-skills --skill peft-fine-tuning --agent claude-code

Installs into .claude/skills of the current project.

Files

PEFT (Parameter-Efficient Fine-Tuning)

Fine-tune LLMs by training <1% of parameters using LoRA, QLoRA, and 25+ adapter methods.

When to use PEFT

Use PEFT/LoRA when:

Fine-tuning 7B-70B models on consumer GPUs (RTX 4090, A100)
Need to train <1% parameters (6MB adapters vs 14GB full model)
Want fast iteration with multiple task-specific adapters
Deploying multiple fine-tuned variants from one base model

Use QLoRA (PEFT + quantization) when:

Fine-tuning 70B models on single 24GB GPU
Memory is the primary constraint
Can accept ~5% quality trade-off vs full fine-tuning

Use full fine-tuning instead when:

Training small models (<1B parameters)
Need maximum quality and have compute budget
Significant domain shift requires updating all weights

Quick start

Installation

# Basic installation
pip install peft

# With quantization support (recommended)
pip install peft bitsandbytes

# Full stack
pip install peft transformers accelerate bitsandbytes datasets