# adapter-hub/adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

Repository: https://github.com/adapter-hub/adapters
Canonical: https://ross.abutalabs.com/products/adapters
Homepage: https://docs.adapterhub.ml
Language: Python
License: Apache-2.0
License Family: permissive
Topics: nlp, natural-language-processing, adapters, transformers, bert, pytorch, parameter-efficient-learning, parameter-efficient-tuning, lora
Last push: 2026-04-26T19:52:02+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 79, release rhythm 69, longevity 100
- inputs: {"age_days": 2325, "days_push": 129, "days_rel": 129, "gap_med": 80.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2826, forks 373 (observed 2026-08-28T04:07:24.208315+00:00)

## What it is
Adapters is a Python add-on library for HuggingFace Transformers that integrates 10+ parameter-efficient fine-tuning methods (bottleneck adapters, LoRA, Prefix Tuning, DoRA, etc.) into 20+ Transformer models. It provides a unified interface for training, composing, merging, and sharing adapter modules for modular transfer learning in NLP.

## Use cases
- fine-tune large language models with LoRA or QLoRA on limited GPU memory
- train multiple task adapters on one shared base Transformer model
- compose or merge adapters via task arithmetics and composition blocks
- run quantized parameter-efficient training like Q-LoRA on Llama models
- share and load pre-trained adapter modules from a central hub
- research parameter-efficient transfer learning methods for NLP
- swap task-specific heads and adapters dynamically for multi-task inference

## When to choose
- you already use HuggingFace Transformers and want adapters or LoRA-style PEFT with a unified API
- you need to train, stack, fuse, or merge multiple adapters on shared base models
- you want quantized low-memory fine-tuning of large language models
- you need compatibility with adapters trained via the legacy adapter-transformers package

## When to avoid
- you need full fine-tuning of all model parameters rather than parameter-efficient methods
- your work is outside NLP/Transformer language models
- you prefer a different PEFT ecosystem such as HuggingFace PEFT and don't need adapter composition features

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-training, nlp
- domain: machine-learning, deep-learning, large-language-models
- platform: python
- tags: parameter-efficient-fine-tuning, peft, adapters, lora, transformers, huggingface, transfer-learning, pytorch, natural-language-processing

## Member repositories
- adapter-hub/adapters (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:24.208315+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:48:41.312592+00:00, confidence not recorded.
  - readme: https://github.com/adapter-hub/adapters (fetched 2026-08-28T04:07:24.208315+00:00, sha 1fcb001681e1)
  - homepage: https://docs.adapterhub.ml (fetched 2026-08-29T09:53:38.684763+00:00, sha d297de1f5e36)
  - site_page: https://docs.adapterhub.ml/quickstart.html (fetched 2026-08-29T09:53:38.695897+00:00, sha 6f93246cd3cf)
  - site_page: https://docs-legacy.adapterhub.ml (fetched 2026-08-29T09:53:38.697480+00:00, sha c78322f7ff94)
  - site_page: https://docs.adapterhub.ml/transitioning.html (fetched 2026-08-29T09:53:38.699504+00:00, sha 9b93b11410ec)
  - site_page: https://docs.adapterhub.ml/installation.html (fetched 2026-08-29T09:53:38.694143+00:00, sha 067046f6585c)
  - registry_pypi: https://pypi.org/pypi/adapters/json (fetched 2026-08-29T09:53:38.701097+00:00, sha deed1dbf835b)
- Data as of 2026-08-30T08:39:29.467469+00:00.