This Repository is an up-to-date version of Harvard nlp's Legacy code and a Refactoring of the jupyter notebook version as a shell script version.

Overview

2022_the_annotated_transformer

Goal

This Repository is an up-to-date version of Harvard nlp's Legacy code and a Refactoring of the jupyter notebook version as a shell script version.

Key points

  • We have re-factored Harvard NLP's Annotated Trasformer into a shell script version.

  • Dataset utilized Multi30K. (The dataset is small, so you can see the results quickly even on computers with low specifications.)

  • We provide the Colab version along with the shell script version, making it easy to modify the model and test the method.

    https://colab.research.google.com/drive/1SrRmC_Ti8IepeHFNBZBjNxl_wkTSJReC?usp=sharing

  • Loss Graph can be drawn.

  • BLEU Score can be measured.

file structure

├── models
│   ├── __init__.py
│   ├── blocks
│   │   ├── __init__.py
│   │   ├── decoder_layer.py
│   │   ├── encoder_layer.py
│   ├── embedding
│   │   ├── __init__.py
│   │   ├── positional_encoding.py
│   │   └── token_embedding.py
│   ├── layers
│   │   ├── __init__.py
│   │   ├── layer_norm.py
│   │   ├── multi_headed_attention.py
│   │   ├── position_wise_feed_forward.py
│   │   └── sublayer_connection.py
│   ├── model
│   │   ├── __init__.py
│   │   ├── decoder.py
│   │   ├── encoder_decoder.py
│   │   ├── encoder.py
│   │   ├── generator.py
│   └── util.py
├── result
│   ├── loss_graph.png
│   ├── train_loss.txt
│   └── valid_loss.txt
├── saved
├── utils
    ├── __init__.py
    ├── batch.py
    ├── batch_size_fn.py
    ├── bleu.py
    ├── data_loader.py
    ├── epoch_time.py
    ├── greedy_decode.py
    ├── label_smoothing.py
    ├── make_model.py
    ├── NoamOpt.py
    ├── run_epoch.py
    ├── simple_loss_compute.py
    └── tokenizer.py
├── README.md
├── test.py
├── train.py
├── config.py
├── data.py
└── graph.py

Training Result

Train Validation loss graph

image

Test set(unseen data) Translation Example

image

Test set(unseen data) BLEU Score Average: 35.870847920953594

Reference

https://nlp.seas.harvard.edu/2018/04/03/attention.html

https://jalammar.github.io/illustrated-transformer/

https://www.facebook.com/groups/TensorFlowKR/permalink/1618169785190740/

https://github.com/hyunwoongko/transformer

Owner
신재욱
신재욱
A piece of software that shows a traceroute of a URL redirect path

Tracing URL redirects has never been easier! Usage • Download 🚩 Use Cases To see where an affiliate link ends up To see what affiliate network is bei

41 Nov 22, 2022
pwncat module that automatically exploits CVE-2021-4034 (pwnkit)

pwncat_pwnkit Introduction The purpose of this module is to attempt to exploit CVE-2021-4034 (pwnkit) on a target when using pwncat. There is no need

Dana Epp 33 Jul 01, 2022
Advanced subdomain scanner, any domain hidden subdomains

little advanced subdomain scanner made in python, works very quick and has options to change the port u want it to connect for

Nano 5 Nov 23, 2021
Security audit Python project dependencies against security advisory databases.

Security audit Python project dependencies against security advisory databases.

52 Dec 17, 2022
Exploiting CVE-2021-44228 in VMWare Horizon for remote code execution and more.

Log4jHorizon Exploiting CVE-2021-44228 in VMWare Horizon for remote code execution and more. BLOG COMING SOON Code and README.md this time around are

96 Dec 14, 2022
MITMSDR for INDIAN ARMY cybersecurity hackthon

There mainly three things here: MITMSDR spectrum Manual reverse shell MITMSDR Installation Clone the project and run the setup file: ./setup One of th

2 Jul 26, 2022
A Python Tool that uses Shodan API's to perform quick recon for vulnerabilities

Shodan Quick Recon A Python Tool that uses Shodan API's to perform quick recon for vulnerabilities Configuration You must edit the python code, and in

Black Hat Ethical Hacking 5 Aug 09, 2022
This program is a WiFi cracker, you can test many passwords for a desired wifi to find the wifi password!

WiFi_Cracker About the Program: This program is a WiFi cracker! Just run code and select a desired wifi to start cracking 💣 Note: you can use this pa

Sina.f 13 Dec 08, 2022
This script allows you to make a onion host instantly.

Installation It only works in Debian based Linux distros. Clone the repo: git clone https://github.com/0xStevenson/Auto-Tor-Host.git Go to the direct

Steven 4 Feb 22, 2022
Phishing Campaign Toolkit

King Phisher Phishing Campaign Toolkit Installation For instructions on how to install, please see the INSTALL.md file. After installing, for instruct

RSM US LLP 1.9k Jan 01, 2023
md5 hash cracking with python.

Python-Md5-Cracker- md5 hash cracking with python. Original files added First create a file called word.txt then run the wordCreate.py script The task

Nebil Sharifi 0 Aug 31, 2022
CVE-2022-22963 PoC

CVE-2022-22963 CVE-2022-22963 PoC Slight modified for English translation and detection of https://github.com/chaosec2021/Spring-cloud-function-SpEL-R

Nicolas Krassas 104 Dec 08, 2022
vulnerable APIs

vulnerable-apis vulnerable APIs inspired by https://github.com/mattvaldes/vulnerable-api Setup Docker If, Out of the box docker pull kmmanoj/vulnerabl

9 Jun 01, 2022
Bypass ReCaptcha: A Python script for dealing with recaptcha

Bypass ReCaptcha Bypass ReCaptcha is a Python script for dealing with recaptcha.

Marcos Camargo 1 Jan 11, 2022
2021hvv漏洞汇总

清单 披露时间 涉及商家/产品 漏洞描述 2021/04/08 启明星辰天清汉马USG防火墙存在逻辑缺陷漏洞(历史漏洞) CNVD-2021-17391 启明星辰 天清汉马USG防火墙 逻辑缺陷漏洞 CNVD-2021-12793 2021/04/08 禅道项目管理软件11.6 禅道 11.6 sq

555 Jan 02, 2023
This exploit allows to connect to the remote RemoteMouse 3.008 service to virtually press arbitrary keys and execute code on the machine.

RemoteMouse-3.008-Exploit The RemoteMouse application is a program for remotely controlling a computer from a phone or tablet. This exploit allows to

Podalirius 25 Dec 04, 2022
A toolkit for web reconnaissance, it's fast and easy to use.

A toolkit for web reconnaissance, it's fast and easy to use. File Structure httpsuite/ main.py init.py db/ db.py init.py subdomains_db directories_db

whoami security 22 Jul 22, 2022
CamRaptor is a tool that exploits several vulnerabilities in popular DVR cameras to obtain device credentials.

CamRaptor is a tool that exploits several vulnerabilities in popular DVR cameras to obtain device credentials.

EntySec 118 Dec 24, 2022
A simple Log4Shell Scan with python

🐞 Log4Scan 🔧 Log4Shell 简单的主动和被动扫描脚本 Log4scan 针对header头和fuzz参数的主动批量扫描,用于大批量黑盒检测

nul1 6 Aug 04, 2022
Xteam All in one Instagram,Android,phishing osint and wifi hacking tool available

Xteam All in one Instagram,Android,phishing osint and wifi hacking tool available

xploits tech 283 Dec 29, 2022