PEFT
Hugging Face Parameter-Efficient Fine-Tuning library (LoRA and related methods) for adapting large models without full fine-tuning.
Tags
Description
Established Apache-2.0 library (huggingface/peft; not archived; not a 2026 launch). PyPI peft 0.21.2 verified 2026-11-11; docs https://huggingface.co/docs/peft/index verified 2026-11-12 (https://huggingface.co/docs/peft redirects there). Install with pip install peft. Commonly paired with transformers and TRL. Model licenses, checkpoints and compute are separate.
Agent access
Related
- TRL: Hugging Face Transformer Reinforcement Learning library for post-training methods such as SFT, DPO, PPO and GRPO on top of transformers.
- Unsloth: Open-source LLM fine-tuning library and desktop app for running and training models locally, with a dual Apache-2.0 / AGPL-3.0 license split.
- Axolotl: Apache-2.0 post-training / fine-tuning framework for a wide range of LLMs, with CLI, YAML configs, Docker and distributed-training options.
- LLaMA-Factory: Apache-2.0 toolkit to fine-tune 100+ LLMs and VLMs via zero-code CLI and the LLaMA Board Gradio web UI.
Guides & comparisons
- Fine-tuning frameworks compared — Axolotl, LLaMA-Factory and Unsloth (Comparison): Compare Axolotl, LLaMA-Factory and Unsloth as SFT, LoRA/QLoRA and preference-tuning frameworks for tool-use models: documented methods, config style, chat/tool datasets, hardware backends, licences and current versions. Cross-links the agent RL stacks comparison.
- Post-training a tool-use model — TRL, PEFT, and scale-out RL (Stack): A recommended post-training stack for chat and tool-use models: TRL and PEFT for SFT, LoRA/QLoRA, DPO and GRPO, with OpenRLHF and AReaL as the distributed and asynchronous RL options. Cross-links the fine-tuning frameworks and agent RL stacks comparisons.
Sources
- https://github.com/huggingface/peft
- https://github.com/huggingface/peft/blob/main/LICENSE
- https://pypi.org/project/peft/
- https://huggingface.co/docs/peft/index
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)