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
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
For when you really need to rank things

Comparisonator For when you really need to rank things. Do you know that feeling when there's this urge deep within you that tells you to compare thin

Maciej Wilczyński 1 Nov 01, 2021
Scripts to convert the Ted-MDB corpora into the formats for DISRPT shared task and the converted corpora

Scripts to convert the Ted-MDB corpora into the formats for DISRPT shared task and the converted corpora.

1 Feb 08, 2022
The most widely used Python to C compiler

Welcome to Cython! Cython is a language that makes writing C extensions for Python as easy as Python itself. Cython is based on Pyrex, but supports mo

7.6k Jan 03, 2023
A supercharged version of paperless: scan, index and archive all your physical documents

Paperless-ng Paperless (click me) is an application by Daniel Quinn and contributors that indexes your scanned documents and allows you to easily sear

Jonas Winkler 5.3k Jan 09, 2023
This project is about for notifying moderators about uploaded photos on server.

This project is about for notifying moderators (people who moderate data from photos) about uploaded photos on server.

1 Nov 24, 2021
Pylexa - Artificial Assistant made with Python

Pylexa - Artificial Assistant made with Python Alexa is a famous artificial assistant used massively across the world. It is a substitute of Alexa whi

\_PROTIK_/ 4 Nov 03, 2021
A browser login credentials thief for windows and Linux

Thief 🦹🏻 A browser login credentials thief for windows and Linux Python script to decrypt login credentials from browsers in windows or linux Decryp

Ash 1 Dec 13, 2021
sawa (ꦱꦮ) is an open source programming language, an interpreter to be precise, where you can write python code using javanese character.

ꦱꦮ sawa (ꦱꦮ) is an open source programming language, an interpreter to be precise, where you can write python code using javanese character. sawa iku

Rony Lantip 307 Jan 07, 2023
Fabric mod where anyone can PR anything, concerning or not. I'll merge everything as soon as it works.

Guess What Will Happen In This Fabric mod where anyone can PR anything, concerning or not (Unless it's too concerning). I'll merge everything as soon

anatom 65 Dec 25, 2022
Pyrmanent - Make all your classes permanent in a flash 💾

Pyrmanent A base class to make your Python classes permanent in a flash. Features Easy to use. Great compatibility. No database needed. Ask for new fe

Sergio Abad 4 Jan 07, 2022
Sequence clustering and database creation using mmseqs, from local fasta files

Sequence clustering and database creation using mmseqs, from local fasta files

Ana Julia Velez Rueda 3 Oct 27, 2022
Python Excuse Generator

Excuse Generator Python Excuse Generator This project is an excuse generator that provides the user with an excuse as to why they weren't paying atten

Collin Sanders 5 Jul 07, 2022
Github dorking tool

gh-dork Supply a list of dorks and, optionally, one of the following: a user (-u) a file with a list of users (-uf) an organization (-org) a file with

Molly White 119 Dec 21, 2022
Anonfiles files leaker via keyword.

Anonfiles files leaker via keyword

Trac3D1y 6 Nov 23, 2022
We are building an open database of COVID-19 cases with chest X-ray or CT images.

🛑 Note: please do not claim diagnostic performance of a model without a clinical study! This is not a kaggle competition dataset. Please read this pa

Joseph Paul Cohen 2.9k Dec 30, 2022
A fishing bot script written in Python!

A fishing bot script written in Python!

Anel Drocic 3 Nov 03, 2021
Skull shaped MOSFET cells for the Efabless's 130nm process

SkullFET Skull shaped MOSFET cells for the Efabless's 130nm process List of cells Inverter Copyright (C) 2021 Uri Shaked

Wokwi 3 Dec 14, 2022
AHP Calculator - A method for organizing and evaluating complicated decisions, using Maths and Psychology

AHP Calculator - A method for organizing and evaluating complicated decisions, using Maths and Psychology

16 Aug 08, 2022