# thunlp/OpenDelta

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

Repository: https://github.com/thunlp/OpenDelta
Canonical: https://ross.abutalabs.com/products/opendelta
Homepage: https://opendelta.readthedocs.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: nlp, nlp-library, pretrained-language-model, parameter-efficient-learning, deep-learning
Last push: 2024-09-19T08:33:56+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1661, "days_push": 713, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1046, forks 83 (observed 2026-08-28T04:03:21.618512+00:00)

## What it is
OpenDelta is a Python library for parameter-efficient tuning (delta tuning) of pretrained language models, letting users attach small trainable modules like adapters, LoRA, or prefix-tuning while freezing the rest. It plugs into PyTorch and Hugging Face Transformers models with flexible, name-based module addressing.

## Use cases
- fine-tune large language models with LoRA instead of full fine-tuning
- add adapters to a pretrained transformer while freezing base weights
- implement prefix tuning or soft prompt tuning on BART or T5
- serve multiple tasks from one frozen PLM with small delta modules
- reduce GPU memory and storage costs when fine-tuning pretrained models
- experiment with parameter-efficient learning methods on Hugging Face models

## When to choose
- you want plug-and-play parameter-efficient tuning on PyTorch/Transformers models
- you need to swap between adapter, LoRA, prefix-tuning, and other delta methods
- you want space-saving multitask serving with a shared frozen backbone

## When to avoid
- you need full fine-tuning of all model parameters
- you work outside PyTorch or with non-Transformers model architectures
- you need actively maintained support for the latest LLM architectures

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp
- domain: machine-learning, deep-learning
- platform: python
- tags: parameter-efficient-tuning, delta-tuning, lora, adapters, prefix-tuning, pytorch, transformers, prompt-tuning, natural-language-processing

## Member repositories
- thunlp/OpenDelta (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.618512+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 2026-08-30T07:02:00.102382+00:00, confidence not recorded.
  - readme: https://github.com/thunlp/OpenDelta (fetched 2026-08-28T04:03:21.618512+00:00, sha a70cbbf90e28)
  - registry_pypi: https://pypi.org/pypi/opendelta/json (fetched 2026-08-29T13:03:30.727375+00:00, sha 5a36bbf7fbbc)
- Data as of 2026-08-30T08:39:29.467469+00:00.