Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A plug-and-play library for parameter-efficient-tuning (Delta Tuning)
| Date | Stars |
|---|---|
| 2026-07-24 | 1045 |
| 2026-07-25 | 1045 |
| 2026-07-28 | 1045 |
| 2026-07-30 | 1045 |
| 2026-08-06 | 1045 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <img src="https://s4.ax1x.com/2022/02/14/Hy7lAf.png" width="350px"> **An Open-Source Framework for Parameter-Efficient Tuning (Delta Tuning).** ------ <p align="center"> <a href="#Overview">Overview</a> • <a href="#installation">Installation</a> • <a href="https://opendelta.readthedocs.io/en/latest/notes/usage.html">Basic Usage</a> • <a href="https://opendelta.readthedocs.io/">Docs</a> • <a href="https://docs.google.com/spreadsheets/d/1BIVa8ocAPga-u7rBOXLYaTfaJSjI1dWfwohmLjmFDrY/edit?usp=sharing">Performance</a> • </p> </div>  ## Overview OpenDelta is a toolkit for parameter-efficient tuning 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 parameters frozen. By using OpenDelta, users could easily implement prefix-tuning, adapters, Lora, or any other types of delta tuning with preferred PTMs. - The latest version of OpenDelta is tested on Python==3.8.13, PyTorch==1.12.1, transformers==4.22.2. Other versions are likely to be supported as well. If you encounter bugs when using your own package versions, please raise an issue, we will look into it as soon as possible. - **A demo of using OpenDelta to modify the PLM (E.g., BART).**  ## News - **2022.10.25** Release v0.3.2. Support [BMTrain]()! Improve docs. Add inspect utilities. - **2022.10.14** Release v0.3.0. We make the usage of default configurations of each delta tuning methods (i.e., the position they are attached) more friendly! If a custom model has our supported models as submodules inside, the default configuration is also available. Other key changes can be seen in [Update Log](https://opendelta.readthedocs.io/en/latest/notes/update.html#version-0-3-0) - **2022.10.10** Merge a long-developed branch v0.2.4 into the master branch. Key updates are (1) the an example unifying the delta tuning paradigm and the prompt-tuning paradigm; (2) and support for [Delta Center](https://www.openbmb.org/toolKits/deltacenter), whose webpage is still under construction. Details can be seen in [Update Log](https://opendelta.readthedocs.io/en/latest/notes/update.html#version-0-2-4) - **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](https://colab.research.google.com/drive/1uAhgAdc8Qr42UKYDlgUv0f7W1-gAFwGo?usp=sharing) to illustrate efficient training and space-saving multitask-serving. - **2022.03.20** A new pip version released. - **2022.02.16** Support [regular expression](https://opendelta.readthedocs.io/en/latest/notes/namebasedaddr.html#regexexpr) in named-based addressing. ## Installation 1. create a virtualenv (optional) ```shell conda create -n opendelta_env python=3.8 conda activate opendelta_env ``` 2. install the latest version ```bash pip install git+https://github.com/thunlp/OpenDelta.git ``` **or** install the latest pip version (more stable) ```bash pip install opendelta ``` **or** build from source ```bash git clone [email protected]:thunlp/OpenDelta.git cd OpenDelta python setup.py install # python setup.py develop # if you want to do some modifications on the code for your research: ``` ## Must Try The following codes and comments walk you through the key functionality of OpenDelta. It is also in [must_try.py](https://github.com/thunlp/OpenDelta/tree/main/examples/unittest/must_try.py) and [must_try.ipynb in Colab](https://colab.research.google.com/drive/1Nbe9zxt8LGQnKmtvEs07IN_PznjNCyk4?usp=sharing). ```python # use transformers as usual. from transformers import AutoModelForSeq2SeqLM, AutoTokenizer t5 = AutoModelForSeq2SeqLM.from_pretrained("t5-large") t5_tokenize
Excerpt of 7,829 characters
Read on GitHub
DingDing · @tsinghua
108
William · Tsinghua University
18
StingNing · Tsinghua University
9
7
5
xiaocj · Tsinghua University · China
2
Zhiyuan Liu · Tsinghua University · China
2
2
1
1
1
1
1
1
Guspan Tanadi
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ddc98852af37a4d2, topic:deep-learning
matched fp:ddc98852af37a4d2, topic:nlp