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
Now patched 0day for force reseting an accounts password

Animal Jam 0day No-Auth Force Password Reset via API Now patched 0day for force reseting an accounts password Used until patched to cause anarchy. Pro

IRIS 10 Nov 17, 2022
Password Manager is a simple Python project which helps users in managing their passwords in a easier way

Password Manager is a simple Python project which helps users in managing their passwords in a easier way

Manish Jalui 4 Sep 29, 2021
A python script to decrypt media files encrypted using the Android application 'Decrypting 'LOCKED Secret Calculator Vault''. Will identify PIN / pattern.

A python script to decrypt media files encrypted using the Android application 'Decrypting 'LOCKED Secret Calculator Vault''. Will identify PIN / pattern.

3 Sep 26, 2022
IDA loader for Apple's iBoot, SecureROM and AVPBooter

IDA iBoot Loader IDA loader for Apple's iBoot, SecureROM and AVPBooter Installation Copy iboot-loader.py to the loaders folder in IDA directory. Credi

matteyeux 74 Dec 23, 2022
It is a very simple XSS simulator based on flask, python.

It is a very simple XSS simulator based on flask, python. The purpose of making this is for teaching the concept of XSS.

Satin Wuker 3 May 10, 2022
VPN Overall Reconnaissance, Testing, Enumeration and eXploitation Toolkit

Vortex VPN Overall Reconnaissance, Testing, Enumeration and Exploitation Toolkit Overview A very simple Python framework, inspired by SprayingToolkit,

315 Dec 28, 2022
解密哥斯拉webshell管理工具流量

kingkong 解密哥斯拉Godzilla-V2.96 webshell管理工具流量 目前只支持jsp类型的webshell流量解密 Usage 获取攻击者上传到服务器的webshell样本 获取wireshark之类的流量包,一般甲方有科来之类的全流量镜像设备,联系运维人员获取,这里以test.

h4ck for fun 46 Dec 21, 2022
Hacktricks - Welcome to the page where you will find each trick/technique/whatever I have learnt in CTFs, real life apps, and reading researches and news.

Hacktricks - Welcome to the page where you will find each trick/technique/whatever I have learnt in CTFs, real life apps, and reading researches and news.

Carlos Polop 5.8k Jan 07, 2023
Bug Alert: a service for alerting security and IT professionals of high-impact and 0day vulnerabilities

Bug Alert Bug Alert is a service for alerting security and IT professionals of h

BugAlert.org 208 Dec 15, 2022
the metasploit script(POC/EXP) about CVE-2021-22005 VMware vCenter Server contains an arbitrary file upload vulnerability

CVE-2021-22005-metasploit the metasploit script(POC/EXP) about CVE-2021-22005 VMware vCenter Server contains an arbitrary file upload vulnerability pr

Taroballz 25 Nov 15, 2022
Reverse engineered Parler API

Parler's unofficial API with all endpoints present in their iOS app as of 08/12/2020. For the most part undocumented, but the error responses are alre

393 Nov 26, 2022
Log4j minecraft with python

Apache-Log4j Apache Log4j 远程代码执行 攻击者可直接构造恶意请求,触发远程代码执行漏洞。漏洞利用无需特殊配置,经阿里云安全团队验证,Apache Struts2、Apache Solr、Apache Druid、Apache Flink等均受影响 Steps 【Import

manmade 57 Oct 03, 2022
NExfil is an OSINT tool written in python for finding profiles by username.

NExfil is an OSINT tool written in python for finding profiles by username. The provided usernames are checked on over 350 websites within few seconds.

thewhiteh4t 1.4k Jan 01, 2023
Domain abuse scanner covering domainsquatting and phishing keywords.

🦷 monodon 🐋 Domain abuse scanner covering domainsquatting and phishing keywords. Setup Monodon is a Python 3.7+ programm. To setup on a Linux machin

2 Mar 15, 2022
A bare-bones POC container runner in python

pybox A proof-of-concept bare-bones container written in 50 lines of python code. Provides namespace isolation and resource limit control Usage Insta

Anirudh Haritas Murali 5 Jun 03, 2021
Searches through git repositories for high entropy strings and secrets, digging deep into commit history

truffleHog Searches through git repositories for secrets, digging deep into commit history and branches. This is effective at finding secrets accident

Truffle Security 10.1k Jan 09, 2023
Exploit tool for Adminer 1.0 up to 4.6.2 Arbitrary File Read vulnerability

AdminerRead Exploit tool for Adminer 1.0 up to 4.6.2 Arbitrary File Read vulnerability Installation git clone https://github.com/p0dalirius/AdminerRea

Podalirius 58 Dec 05, 2022
KeyKatcher is a keylogger that records keystrokes made on a computer and sends to the E-Mail.

What is a keylogger? A keylogger is a software application or piece of hardware that monitors and records keystrokes made on a computer keyboard. The

Himank_Jain 7 Sep 19, 2022
Python exploit for vsftpd 2.3.4 - Backdoor Command Execution

CVE-2011-2523 - vsftpd 2.3.4 Exploit Discription vsftpd, which stands for Very Secure FTP Daemon,is an FTP server for Unix-like systems, including Lin

Padsala Tushal 5 Nov 08, 2022
Let's you scan the entire internet in a couple of hours and identify all Minecraft servers on IPV4

Minecraft-Server-Scanner Let's you scan the entire internet in a couple of hours and identify all Minecraft servers on IPV4 Installation and running i

116 Jan 08, 2023