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
Shell scripts made simple 🐚

zxpy Shell scripts made simple 🐚 Inspired by Google's zx, but made much simpler and more accessible using Python. Rationale Bash is cool, and it's ex

Tushar Sadhwani 492 Dec 27, 2022
Helps compare between New and Old Tax Regime.

Income-Tax-Calculator Helps compare between New and Old Tax Regime. Sample Console Input/Output

2 Jan 10, 2022
Repo to demo translating colab/jupyter notebook to streamlit webapp

Repo to demo translating colab/jupyter notebook to streamlit webapp

Marisa Smith 2 Feb 02, 2022
A program that analyzes data from inertia measurement units installeed in aircraft and generates g-exceedance curves

A program that analyzes data from inertia measurement units installeed in aircraft and generates g-exceedance curves

Pooya 1 Nov 23, 2021
Ingest openldap data into bloodhound

Bloodhound for Linux Ingest a dumped OpenLDAP ldif into neo4j to be visualized in Bloodhound. Usage: ./ldif_to_neo4j.py ./sample.ldif | cypher-shell -

Guillaume Quéré 71 Nov 09, 2022
Free version of Okuru selfbot, okuru.xyz

Indigo Selfbot Free OpenSource selfbot, Premium version can be found at https://okuru.xyz (5$.) Usage python[3] main.py Installation To install you ca

Dimitri Demarkus 31 Aug 07, 2022
Script that creates graphical representations of Julia an Mandelbrot sets.

Julia and Mandelbrot Picture Maker This simple functions create simple plots of the Julia and Mandelbrot sets. The Julia set require the important par

Juan Riera Gomez 1 Jan 10, 2022
The Python agent for Apache SkyWalking

SkyWalking Python Agent SkyWalking-Python: The Python Agent for Apache SkyWalking, which provides the native tracing abilities for Python project. Sky

The Apache Software Foundation 149 Dec 12, 2022
WinBoost: Boost your windows system.

Winboost runs a complete checkup of your entire system locating junk files, speed-reducing issues and causes of any system or application glitches or crashes. Through a lot of research and testing, w

Smit Parmar 4 Oct 01, 2021
SEH-Helper - Binary Ninja plugin for exploring Structured Exception Handlers

SEH Helper Author: EliseZeroTwo A Binary Ninja helper for exploring structured e

Elise 74 Dec 26, 2022
Markov Chain Composer

Markov Chain Composer Using Markov Chain to represent relationships between words in song lyrics and then generating new lyrics.. ahem interpretive po

Kylie 85 Dec 09, 2022
Better firefox bookmarks script for rofi

rofi-bookmarks Small python script to open firefox bookmarks with rofi. Features Icons! Only show bookmarks in a specified bookmark folder Show entire

32 Nov 10, 2022
Simple cash register system made with guizero

Eje-Casher なにこれ guizeroで作った簡易レジシステムです。実際にコミケで使う予定です。 これを誰かがそのまま使うかどうかというよりは、guiz

Akira Ouchi 4 Nov 07, 2022
Stop ask your soraka to ult you, just ult yourself

Lollo's auto-ultimate script Are you tired of your low elo friend who can't ult you with soraka when you ask for it? Use Useless Support and just ult

9 Oct 20, 2022
Really bad lisp implementation. Fun with pattern matching.

Lisp-py This is a horrible, ugly interpreter for a trivial lisp. Don't use it. It was written as an excuse to mess around with the new pattern matchin

Erik Derohanian 1 Nov 23, 2021
You can easily send campaigns, e-marketing have actually account using cash will thank you for using our tools, and you can support our Vodafone Cash +201090788026

*** Welcome User Sorry I Mean Hello Brother ✓ Devolper and Design : Mokhtar Abdelkreem ========================================== You Can Follow Us O

Mo Code 1 Nov 03, 2021
Perform oocyst segmentation in mercurochrome stained mosquito midgut

Midgut_oocyst_segmentation Perform oocyst segmentation in mercurochrome stained mosquito midguts This oocyst segmentation model also powers the webtoo

Duo Peng 3 Oct 27, 2021
Life Dynamics for python

Daphny_counter run command must be like this: /usr/bin/python3 /home/nmakagonov/Daphny/daphny_counter/Daphny_counter.py -o /home/nmakagonov/Daphny/out

12 Sep 05, 2022
This repository contains all the data analytics projects that I've worked on in python.

93_Python_Data_Analytics_Projects This repository contains all the data analytics projects that I've worked on in python. No. Name 01 001_Cervical_Can

Milaan Parmar / Милан пармар / _米兰 帕尔马 267 Jan 06, 2023
🎴 LearnQuick is a flashcard application that you can study with decks and cards.

🎴 LearnQuick is a flashcard application that you can study with decks and cards. The main function of the application is to show the front sides of the created cards to the user and ask them to guess

Mehmet Güdük 7 Aug 21, 2022