DOP-Tuning(Domain-Oriented Prefix-tuning model)

Overview

DOP-Tuning

DOP-Tuning(Domain-Oriented Prefix-tuning model)代码基于Prefix-Tuning改进.

Files

├── seq2seq                       # Code for encoder-decoder architecture
│   ├── train_bart.py             # high-level scripts to train.
│   ├── prefixTuning.py           # code that implements prefix-tuning.
│   ├── finetune.py               # training code (contains data loading, model loading, and calls trainer)   
│   ├── lightning_base.py         # helper code
│   ├── utils.py                  # helper code
│   └── callbacks.py              # helper code
└── ...

To run the code for encoder-decoder architecture like BART, the code is in seq2seq. This corresponds to the summarization experiments in the paper.

Setup:

cd transformer; pip install -e .

Train via DOP-tuning

cd seq2seq; 

python train_bart.py --mode xsum --preseqlen 200 --do_train yes --fp16 yes --bsz 16  --epoch 30  --gradient_accumulation_step 3 --learning_rate 0.00005  --mid_dim 800 --use_lowdata_token 'yes' --lowdata_token 'summarize'

其中use_lowdata_token表示是否采用domain word初始化的方式;lowdata_token表示传入的domain word.

Decode

cd seq2seq; 

python train_bart.py --mode xsum --do_train no --prefix_model_path {checkpoint_path} --preseqlen {same as training} --mid_dim {same as training} --use_lowdata_token 'yes' --lowdata_token 'summarize'
Owner
Andrew Zeng
Andrew Zeng
Andrew Zeng
Practice in Oxford_AI&ML class

Practice in Oxford_AI&ML class

St3ve Lee 2 Feb 04, 2022
💻 Algo-Phantoms-Backend is an Application that provides pathways and quizzes along with a code editor to help you towards your DSA journey.📰🔥 This repository contains the REST APIs of the application.✨

Algo-Phantom-Backend 💻 Algo-Phantoms-Backend is an Application that provides pathways and quizzes along with a code editor to help you towards your D

Algo Phantoms 44 Nov 15, 2022
A web app for presenting my research in BEM(building energy model) simulation

BEM(building energy model)-SIM-APP The is a web app presenting my research in BEM(building energy model) calibration. You can play around with some pa

8 Sep 03, 2021
A flexible free and unlimited python tool to translate between different languages in a simple way using multiple translators.

deep-translator Translation for humans A flexible FREE and UNLIMITED tool to translate between different languages in a simple way using multiple tran

Nidhal Baccouri 806 Jan 04, 2023
An application for automation of the mining function in the game Alienworlds.IO

alienautomation A Python script made to automate the tidious job of mining on AlienWorlds This script: Automatically opens the browser Automatically l

anonieXdev 42 Dec 03, 2022
This script can be used to get unlimited Gb for WARP.

Warp-Unlimited-GB This script can be used to get unlimited Gb for WARP. How to use Change the value of the 'referrer' to warp id of yours You can down

Anix Sam Saji 1 Feb 14, 2022
Airbrake Python

airbrake-python Note. Python 3.4+ are advised to use new Airbrake Python notifier which supports async API and code hunks. Python 2.7 users should con

Airbrake 51 Dec 22, 2022
The Python Achievements Framework!

Pychievements: The Python Achievements Framework! Pychievements is a framework for creating and tracking achievements within a Python application. It

Brian 114 Jul 21, 2022
Android Blobs Organizer

Android Blobs Organizer

Sebastiano Barezzi 96 Jan 02, 2023
A visidata plugin for parsing f5 ltm/gtm/audit logs

F5 Log Visidata Plugin This plugin supports the default log format for: /var/log/ltm* /var/log/gtm* /var/log/apm* /var/log/audit* It extracts common l

James Deucker 1 Jan 06, 2022
A hackerank problems, solution repository

This is a repository for all hackerank challenges kindly note this is for learning purposes and if you wish to contribute, dont hesitate all submision

Tyler Mwalo Kenneth's 1 Dec 20, 2021
Tomador de ramos UC automatico para Windows, Linux y macOS

auto-ramos v2.0 Tomador de ramos UC automatico para Windows, Linux y macOS Funcion Este script de Python tiene como principal objetivo hacer que la to

Open Source eUC 13 Jun 29, 2022
Runs macOS on linux with qemu.

mac-on-linux-with-qemu Runs macOS on linux with qemu. Pre-requisites qemu-system-x86_64 dmg2img pulseaudio python[click] Usage After cloning the repos

Arindam Das 177 Dec 26, 2022
Chess bot can play automatically as white or black on lichess.com, chess.com and any website using drag and drop to move pieces

Chessbot "Why create another chessbot ?" The explanation is simple : I did not find a free bot I liked online : all the bots I saw on internet are par

Dhimas Bagus Prayoga 2 Nov 11, 2021
This is a Python 3.10 port of mock, a library for manipulating human-readable message strings.

This is a Python 3.10 port of mock, a library for manipulating human-readable message strings.

Alexander Bartolomey 1 Dec 31, 2021
A simple projects to help your seo optimizing has been written with python

python-seo-projects it is a very simple projects to help your seo optimizing has been written with python broken link checker with python(it will give

Amirmohammad Razmy 3 Dec 25, 2021
A comprensive software collection for nmea manipulation

nmeatoolkit A comprensive software collection for nmea manipulation; it includes a library and a collections of command line tools. Library pipes: con

Davide Gessa 1 Sep 14, 2022
poetry2nix turns Poetry projects into Nix derivations without the need to actually write Nix expressions

poetry2nix poetry2nix turns Poetry projects into Nix derivations without the need to actually write Nix expressions. It does so by parsing pyproject.t

Nix community projects 405 Dec 29, 2022
Batch obfuscator based on the obfuscation method used by the trick bot launcher

Batch obfuscator based on the obfuscation method used by the trick bot launcher

SlizBinksman 2 Mar 19, 2022
2021华为软件精英挑战赛 程序输出分析器

AutoGrader 0.2.0更新:加入资源分配溢出检测,如果发生资源溢出会输出溢出发生的位置。 如果通过检测,会显示通过符号 如果没有通过检测,会显示警告,并输出溢出发生的位置和操作

54 Aug 14, 2022