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
This repo will have a small amount of Chrome tools that can be used for DFIR, Hacking, Deception, whatever your heart desires.

Chrome-Tools Overview Welcome to the repo. This repo will have a small amount of Chrome tools that can be used for DFIR, Hacking, Deception, whatever

5 Jun 08, 2022
The repository for my video "Playing MINECRAFT with a WEBCAM"

This is the official repo for my video "Playing MINECRAFT with a WEBCAM" on YouTube Original video can be found here: https://youtu.be/701TPxL0Skg Red

Rishabh 27 Jun 07, 2022
qecsim is a Python 3 package for simulating quantum error correction using stabilizer codes.

qecsim qecsim is a Python 3 package for simulating quantum error correction using stabilizer codes.

44 Dec 20, 2022
A basic animation modding workflow for FFXIV

AnimAssist Provides a quick and easy way to mod animations in FFXIV. You will need: Before anything, the VC++2012 32-bit Redist from here. Havok will

liam 37 Dec 16, 2022
WMIC Serial Checker For Python

WMIC Serial Checker Follow me here: Discord | Github FR: A but éducatif seulement. EN: For educational purposes only. ❓ Informations FR: WMIC Serial C

AkaTool's 0 Apr 25, 2022
An open-source Python project series where beginners can contribute and practice coding.

Python Mini Projects A collection of easy Python small projects to help you improve your programming skills. Table Of Contents Aim Of The Project Cont

Leah Nguyen 491 Jan 04, 2023
Bots in moderation and a game (for now)

Tutorial: come far funzionare il bot e durarlo per 24/7 (o quasi...) Ci sono 17 passi per seguire: Andare sul sito Replit https://replit.com/ Vedrete

ZacyKing 1 Dec 27, 2021
免杀shellcode加载器

bypassAV 条件触发式远控 VT 5/70 免杀国内杀软及defender、卡巴斯基等主流杀软 原理 https://pureqh.top/?p=5412 use 将shellcode填至go_shellcode_encode.py生成混淆后的base64 payload 然后将生成的payl

405 Dec 14, 2022
Script em python, utilizando PySimpleGUI, para a geração de arquivo txt a ser importado no sistema de Bilhetagem Eletrônica da RioCard, no Estado do Rio de Janeiro.

pedido-vt-riocard Script em python, utilizando PySimpleGUI, para a geração de arquivo txt a ser importado no sistema de Bilhetagem Eletrônica da RioCa

Carlos Bruno Gomes 1 Dec 01, 2021
Groupe du projet Python en 2TL2-4

Présentation Projet EpheCom Ce logiciel a été développé dans le cadre scolaire. EpheCom est un logiciel de communications - vocale et écrite - en temp

1 Dec 26, 2021
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
J MBF - Assalamualaikum Mamang...

★ VISITOR ★ ★ INFORMATION ★ Script Ini DiBuat Oleh YayanXD Script Ini Akan DiPerjual Belikan Tanggal 9 Januari 2022 Jika Mau Beli Script Silahkan Hub

Risky [ Zero Tow ] 5 Apr 08, 2022
This is the accompanying repository for the Bloomberg Global Coal Countdown website.

This is the accompanying repository for the Bloomberg Global Coal Countdown (BGCC) website. Data Sources Dashboard Data Schema and Validation License

7 Jun 01, 2022
Projeto job insights - Projeto avaliativo da Trybe do Bloco 32: Introdução à Python

Termos e acordos Ao iniciar este projeto, você concorda com as diretrizes do Código de Ética e Conduta e do Manual da Pessoa Estudante da Trybe. Boas

Lucas Muffato 1 Dec 09, 2021
Code for Crowd counting via unsupervised cross-domain feature adaptation.

CDFA-pytorch Code for Unsupervised crowd counting via cross-domain feature adaptation. Pre-trained models Google Drive Baidu Cloud : t4qc Environment

Guanchen Ding 6 Dec 11, 2022
Script to check if your Bistromatic handle everything as it should.

Bistromatic Checker Script to check if your Bistromatic handle everything as it should. The bistromatic is the project marking the end of the CPool at

Mathias 1 Dec 27, 2021
A git extension for seeing your Cloud Build deployment

A git extension for seeing your Cloud Build deployment

Katie McLaughlin 13 May 10, 2022
Download and archive entire usenet newsgroups over NNTP.

Usenet Archiving Tool This code is for archiving Usenet discussions, not downloading files. Newsgroup posts are saved under the authors name and email

Corey White 2 Dec 23, 2021
Datasets with Softcatalà website content

softcatala-web-dataset This repository contains Sofcatalà web site content (articles and programs descriptions). Dataset are available in the dataset

Softcatalà 2 Dec 26, 2021
This repository contains the code for the python introduction lab

This repository contains the code for the python introduction lab. The purpose is to have a fairly simple python assignment that introduces the basic features and tools of python

1 Jan 24, 2022