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
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
Functions to analyze Cell-ID single-cell cytometry data using python language.

PyCellID (building...) Functions to analyze Cell-ID single-cell cytometry data using python language. Dependecies for this project. attrs(=21.1.0) fo

0 Dec 22, 2021
Python Commodore BBS multi-client

python-cbm-bbs-petscii Python Commodore BBS multi-client This is intended for commodore 64, c128 and most commodore compatible machines (as the new Co

7 Sep 16, 2022
A Red Team tool for exfiltrating sensitive data from Jira tickets.

Jir-thief This Module will connect to Jira's API using an access token, export to a word .doc, and download the Jira issues that the target has access

Antonio Piazza 82 Dec 12, 2022
A sandpit for textual related things

A sandpit repo for testing textual related things.

Craig Gumbley 1 Nov 08, 2021
Collatz Sanısını Test Eden Ve Kanıtlayan Bir Python Programı

Collatz Sanısı Collatz Sanısını Test Eden Ve Kanıtlayan Bir Python Programı. Kullanım Terminalde: 1- git clone https://github.com/detherminal/Collatz-

Cemal Mert 2 May 07, 2022
PREFS is a Python library to store and manage preferences and settings.

PREFS PREFS is a Python library to store and manage preferences and settings. PREFS stores a Python dictionary in a total human-readable file, the PRE

Pat 13 May 26, 2022
Python framework to build apps with the GASP metaphor

Gaspium Python framework to build apps with the GASP metaphor This project is part of the Pyrustic Open Ecosystem. Installation | Documentation | Late

5 Jan 01, 2023
[x]it! support for working with todo and check list files in Sublime Text

[x]it! for Sublime Text This Sublime Package provides syntax-highlighting, shortcuts, and auto-completions for [x]it! files. Features Syntax highlight

Jan Heuermann 18 Sep 19, 2022
Код файнтюнинга оригинального CLIP на русский язык

О чем репозиторий В этом репозитории представлен способ файтюнить оригинальный CLIP на новый язык Почему модель не видит женщину и откуда на картинке

Valentina Biryukova 7 Feb 06, 2022
A simple Python script for generating a variety of hashes from safe urandom entropy.

Hashgen A simple Python script for generating a variety of hashes from safe urandom entropy. For whenever you need a random hash (e.g. generating an a

Xanspie 1 Feb 17, 2022
Design-by-contract in Python3 with informative violation messages and inheritance

icontract icontract provides design-by-contract to Python3 with informative violation messages and inheritance. It also gives a base for a flourishing

275 Jan 02, 2023
This repository contains code for building education startup.

Learning Management System Overview It's the code for EssayBrain, a tool for teacher that automatically grades and validates essays. In order to valid

Shyam Das Shrestha 1 Nov 21, 2021
Anki Cards for the HSK vocabulary Chinese-German

Anki-HanyuShuipingKaoshi Anki Cards for the HSK vocabulary Chinese-German Das Deck baut auf folgenden Quellen auf: China Endecken Wortschatz von wohok

1 Jan 07, 2022
Tool to generate wrappers for Linux libraries allowing for dlopen()ing them without writing any boilerplate

Dynload wrapper This program will generate a wrapper to make it easy to dlopen() shared objects on Linux without writing a ton of boilerplate code. Th

Hein-Pieter van Braam 25 Oct 24, 2022
resultados (data) de elecciones 2021 y código para extraer data de la ONPE

elecciones-peru-2021-ONPE Resultados (data) de elecciones 2021 y código para extraer data de la ONPE Data Licencia liberal, pero si vas a usarlo por f

Ragi Yaser Burhum 21 Jun 14, 2021
Arabic to Roman Converter in Python

Arabic-to-Roman-Converter Made together with https://github.com/goltaraya . Arabic to Roman Converter in Python. -Instructions: 1 - Make sure you have

Pedro Lucas Tomazeti Fernandes 6 Oct 28, 2021
A server shell for you to play with Powered by Django + Nginx + Postgres + Bootstrap + Celery.

A server shell for you to play with Powered by Django + Nginx + Postgres + Bootstrap + Celery.

Mengting Song 1 Jan 10, 2022
Antchain-MPC is a library of MPC (Multi-Parties Computation)

Antchain-MPC Antchain-MPC is a library of MPC (Multi-Parties Computation). It include Morse-STF: A tool for machine learning using MPC. Others: Commin

Alipay 37 Nov 22, 2022
Viewer for NFO files

NFO Viewer NFO Viewer is a simple viewer for NFO files, which are "ASCII" art in the CP437 codepage. The advantages of using NFO Viewer instead of a t

Osmo Salomaa 114 Dec 29, 2022