PEFT

license

Apache-2.0(OSI)

source

public(huggingface/peft)

managed-tier

none

core features withheld

no

Apache-2.0, an OSI license, with the full source public and no proprietary tier.

• https://github.com/huggingface/peft recorded 2026-08-09

  Repository metadata reports "license":{"spdxId":"Apache-2.0","name":"Apache License 2.0"} and "isArchived":false, with description "🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning." The only occurrences of "enterprise" or "premium" in the page are GitHub's own site-wide navigation chrome (Copilot/Enterprise nav links to github.com/enterprise and github.com/pricing) — none reference peft itself, and the page names no gated feature or paid edition of the library.

• https://huggingface.co/pricing recorded 2026-09-23

  Hugging Face's paid plans: PRO at "$9" per month, Team at "$20", Enterprise at "$50", plus per-TB Hub storage and hourly Spaces/inference hardware. Every listed benefit is Hub- or account-scoped (storage, inference credits, SSO, audit logs); a case-insensitive search of the body for "peft" returns zero matches, so no PEFT feature is gated behind a plan.

• https://pypi.org/project/peft/ recorded 2026-09-23

  Project page headed "peft 0.20.0". Sidebar License reads "Apache Software License (Apache)" and the classifier list carries "License :: OSI Approved :: Apache Software License". Provides Extra lists exactly dev, docs-specific, quality and test, matching setup.py — no paid or enterprise extra on the distributed wheel.

• https://raw.githubusercontent.com/huggingface/peft/main/LICENSE recorded 2026-09-23

  Full unmodified Apache License, Version 2.0 text, opening "Apache License / Version 2.0, January 2004 / http://www.apache.org/licenses/" and "TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION", closing with the standard APPENDIX carrying the unfilled template placeholder "Copyright [yyyy] [name of copyright owner]". No added use restriction or field-of-use clause.

• https://raw.githubusercontent.com/huggingface/peft/main/setup.py recorded 2026-09-16

  setup() declares name="peft", license="Apache", license_files=["LICENSE"], and classifiers including "License :: OSI Approved :: Apache Software License". extras_require is limited to quality, docs_specific, dev and test — no commercial or enterprise extra — and package_dir/packages point at the same src/peft tree the repo ships, so the installable package builds from the published source with nothing withheld.

Adoption is measured by PyPI downloads of peft, the canonical LoRA and adapter library and a dependency of TRL and most LoRA fine-tuning stacks.

• https://pypistats.org/api/packages/peft/recent recorded 2026-08-09

  Full JSON body: {"data":{"last_day":471851,"last_month":11691121,"last_week":2916121},"package":"peft","type":"recent_downloads"}: 11,691,121 downloads in the trailing month.

• https://pypistats.org/packages/peft recorded 2026-08-09

  HTML package-statistics page. Rendered text reads "Downloads last month: 11,691,121" and "Downloads last week: 2,916,121", with "Latest version: 0.20.0" — corroborates the API figure from an actively-released package rather than download residue.

PEFT offers reference-grade depth on parameter-efficient methods -- LoRA, QLoRA, AdaLoRA, LoHa, LoKr, IA3 and prefix or prompt tuning -- with 4- and 8-bit quantization, BF16, and parallelism inherited from Accelerate. Its scope stops at adapters: it does not orchestrate full RLHF the way TRL and OpenRLHF do, and it does not train at frontier scale the way Megatron-LM does.

• https://raw.githubusercontent.com/huggingface/peft/main/docs/source/developer_guides/quantization.md recorded 2026-09-28

  The Quantization guide combines PEFT LoRA with bitsandbytes 4-bit quantization, AWQ, GPTQ and AQLM, describing QLoRA as a method "that quantizes a model to 4-bits and then trains it with LoRA" and noting "This method allows you to finetune a 65B parameter model on a single 48GB GPU!". Its worked example sets "bnb_4bit_compute_dtype=torch.bfloat16".

• https://raw.githubusercontent.com/huggingface/peft/main/README.md recorded 2026-09-28

  Quickstart wraps a base model with get_peft_model and a LoraConfig, and the integrations section covers Transformers ("PEFT is directly integrated with [Transformers]"), Diffusers ("conveniently managing different adapters"), Accelerate ("distributed training and inference for really big models") and TRL ("PEFT can also be applied to training LLMs with RLHF components such as the ranker and policy"). The memory table lists a 12B model as "OOM GPU" for full fine-tuning against "56GB GPU / 3GB CPU" with LoRA, and a Stable Diffusion LoRA checkpoint at "only 8.8MB".

• https://raw.githubusercontent.com/huggingface/peft/main/src/peft/utils/peft_types.py recorded 2026-09-28

  The PeftType enum, documented as "Enum class for the different types of adapters in PEFT.", lists 45 method identifiers, among them "LORA", "ADALORA", "IA3", "PROMPT_TUNING", "PREFIX_TUNING", "P_TUNING", "LOHA", "LOKR", "OFT", "VERA" and "BOFT", plus newer additions such as "DELORA", "GRALORA" and "CARTRIDGE". All are adapter-family techniques; none add full-model training orchestration or frontier-scale parallelism.