OpenDeltaMirror/README.md at fix-web

4.4 KiB

Raw Permalink Blame History

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

Overview • Installation • Basic Usage • 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.

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).

Updates

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.

Installation

create a virtualenv (optional)

conda create -n opendelta_env python=3.8
conda activate opendelta_env

Using Pip

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 or keep the repo updated by git clone, run

python setup.py develop

Must Try

from transformers import AutoModelForSeq2SeqLM
t5 = AutoModelForSeq2SeqLM.from_pretrained("t5-base")
from opendelta import AutoDeltaModel
delta = AutoDeltaModel.from_finetuned("DeltaHub/lora_t5-base_mrpc", backbone_model=t5)
delta.log()

Verified Supported Models

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.

	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

Subject to change at any moment.

4.4 KiB Raw Permalink Blame History