xgreat8 / opendelta Goto Github PK

An Open-Source Framework for Paramter-Efficient Tuning (Delta Tuning).

---

Overview • Installation • Basic Usage • Docs • Performance •

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.

• Our repo is tested on Python 3.8 and PyTorch 1.9.0. Lower version may also be supported.

• A demo of using Opendelta to modify the PLM (E.g., BART).

• 2022.03.24 We notice several bugs in Soft Prompt Tuning and Prefix Tuning, mainly due to their need to customize attention ids, token_type_ids, we are fixing it! Currently, please use the other methods since they are stabler and better in performance.
• 2022.03.20 Add a colab example to illustrate efficient training and space-saving multitask-serving.
• 2022.03.20 A new pip version released.
• 2022.02.16 Support regular expression in named-based addressing.

create a virtualenv (optional)

conda create -n opendelta_env python=3.8
conda activate opendelta_env

Install OpenDelta using pip as follows:

pip install opendelta

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

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

python setup.py install

python setup.py develop

from transformers import AutoModelForSeq2SeqLM
t5 = AutoModelForSeq2SeqLM.from_pretrained("t5-large")
from opendelta import AutoDeltaModel
delta = AutoDeltaModel.from_finetuned("thunlp/FactQA_T5-large_Adapter", backbone_model=t5)
delta.log()

• You can try to use OpenDelta on any backbone models based on PyTorch.

• However, with small chances thatThe 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.