An Open-Source Framework for Paramter Efficient Tuning.

---

Overview • Installation • Supported Models • Docs • Performance •

Overview

OpenDelta is a toolkit for parameter efficient methods (we dub it as delta tuning), by which users could flexibly assign (or add) a small amount parameters to update while keeping the most paramters frozen. By using OpenDelta, users could easily implement prefix-tuning, adapters, Lora, or any other types of delta tuning with preferred PTMs.

Installation

create a virtualenv (optional)

conda create -n opendelta_env python=3.8
conda activate opendelta_env

Using Pip

Our repo is tested on Python 3.6+ and PyTorch 1.8.1+, install OpenDelta using pip as follows:

pip install opendelta

To play with the latest features, you can also install OpenDelta from the source.

Build from Source

git clone https://github.com/thunlp/OpenDelta.git
cd OpenDelta

Option 1: If you won't modify the code, run

python setup.py install

Option 2: If you want to modify the code, run

python setup.py develop

Verified Supported Models

** You can try to use OpenDelta on any backbone models based on PyTorch.** However, with small chances that The interface of the submodules of the backbone model is not supported. Therefore we verified some commonly used models that OpenDelta are sure to support.

We will keep testing more and more emerging models.

Pull requests are welcomed when you successfully apply OpenDelta on your own backbone model.

	Lora	Bias Tuning	Adapter Houstbly	Adapter Preffier	Adapter Drop	Adapater Low-Rank	Compactor	Prefix Tuning	Prompt Tuning
T5	✅	✅	✅	✅	✅	✅	✅	✅	✅
GPT-2	✅	✅	✅	✅	✅	✅	✅	✅
BART	✅	✅	✅	✅	✅	✅	✅	✅
DistilBERT	✅	✅	✅	✅	✅	✅	✅	✅
RoBERTa	✅	✅	✅	✅	✅	✅	✅	✅
BERT	✅	✅	✅	✅	✅	✅	✅	✅	✅
T5-3b(parallel)	✅	✅	✅	✅	✅	✅	✅	✅	✅
Deberta-v2	✅	✅	✅	✅	✅	✅	✅
CTRL	✅	✅	✅	✅	✅	✅	✅
ViT	✅

Performance Checked Combination

Google sheet here