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
ProxyLogon Pre-Auth SSRF To Arbitrary File Write

ProxyLogon Pre-Auth SSRF To Arbitrary File Write For Education and Research Usage: C:\python proxylogon.py mail.evil.corp lulz 117 Nov 28, 2022

Auerswald COMpact 8.0B Backdoors exploit

CVE-2021-40859 Auerswald COMpact 8.0B Backdoors exploit About Backdoors were discovered in Auerswald COMpact 5500R 7.8A and 8.0B devices, that allow a

6 Sep 22, 2022
ProxyLogon(CVE-2021-26855+CVE-2021-27065) Exchange Server RCE(SSRF->GetWebShell)

ProxyLogon For Python3 ProxyLogon(CVE-2021-26855+CVE-2021-27065) Exchange Server RCE(SSRF-GetWebShell) usage: python ProxyLogon.py --host=exchang

112 Dec 01, 2022
A simple automatic tool for finding vulnerable log4j hosts

Log4Scan A simple automatic tool for finding vulnerable log4j hosts Installation pip3 install -r requirements.txt Usage usage: log4scan.py [-h] (-f FI

Federico Rapetti 20018955 6 Mar 10, 2022
Bilgi Sistemleri Projesi için yapılan keylogger

Keylogger Bilgi Sistemleri Projesi için yapılan keylogger Projede kullanılan kütüphanelere sahip olmasanız da python dosyası çalıştığında kendisi gere

Tarik Bulut 1 Jan 07, 2022
利用NTLM Hash读取Exchange邮件

GetMail 利用NTLM Hash读取Exchange邮件:在进行内网渗透时候,我们经常拿到的是账号的Hash凭据而不是明文口令。在这种情况下采用邮件客户端或者WEBMAIL的方式读取邮件就很麻烦,需要进行破解,NTLM的破解主要依靠字典强度,破解概率并不是很大。

<a href=[email protected]"> 388 Dec 27, 2022
Visibility and Mitigation for Log4J vulnerabilities

Visibility and Mitigation for Log4J vulnerabilities Several scripts for the visibility and mitigation of Log4J vulnerabilities. Static Scanner - Linux

SentinelLabs 15 May 21, 2022
Omega - From Wordpress admin to pty

The Linux tool to automate the process of getting a pty once you got admin credentials in a Wordpress site. Keep in mind that right now Omega only can attack Linux hosts.

Ángel Heredia 12 Nov 09, 2022
Easily retargetable and hackable interactive disassembler with IDAPython-compatible plugin API

ScratchABit is an interactive incremental disassembler with data/control flow analysis capabilities. ScratchABit is dedicated to the effor

Paul Sokolovsky 380 Dec 28, 2022
Deltaspy - an advanced keylogger that can send keylogs and screenshots to gmail

Deltaspy Deltaspy is a advanced keylogger which sends keylogs and screenshot to

Praanesh S 1 Dec 31, 2021
Repository for a project of the course EP2520 Building Networked Systems Security

EP2520_ACME_Project Repository for a project of the course EP2520 Building Networked Systems Security in Royal Institute of Technology (KTH), Stockhol

1 Dec 11, 2021
Small Python library that adds password hashing methods to ORM objects

Password Mixin Mixin that adds some useful methods to ORM objects Compatible with Python 3.5 = 3.9 Install pip install password-mixin Setup first cre

Joe Gasewicz 5 Nov 22, 2022
Proof of concept for CVE-2021-24086, a NULL dereference in tcpip.sys triggered remotely.

CVE-2021-24086 This is a proof of concept for CVE-2021-24086 ("Windows TCP/IP Denial of Service Vulnerability "), a NULL dereference in tcpip.sys patc

Axel Souchet 220 Dec 14, 2022
automatically crawl every URL and find cross site scripting (XSS)

scancss Fastest tool to find XSS. scancss is a fastest tool to detect Cross Site scripting (XSS) automatically and it's also an intelligent payload ge

Md. Nur habib 30 Sep 24, 2022
A honey token manager and alert system for AWS.

SpaceSiren SpaceSiren is a honey token manager and alert system for AWS. With this fully serverless application, you can create and manage honey token

287 Nov 09, 2022
Patching - Interactive Binary Patching for IDA Pro

Patching - Interactive Binary Patching for IDA Pro Overview Patching assembly code to change the behavior of an existing program is not uncommon in ma

589 Dec 30, 2022
Bandit is a tool designed to find common security issues in Python code.

A security linter from PyCQA Free software: Apache license Documentation: https://bandit.readthedocs.io/en/latest/ Source: https://github.com/PyCQA/ba

Python Code Quality Authority 4.8k Dec 31, 2022
Fuzzercorn - Bring libfuzzer to Unicorn

Fuzzercorn libfuzzer bindings for Unicorn. API // The main entry point of the fu

lazymio 23 Nov 17, 2022
Directory Traversal in Afterlogic webmail aurora and pro

CVE-2021-26294 Exploit Directory Traversal in Afterlogic webmail aurora and pro . Description: AfterLogic Aurora and WebMail Pro products with 7.7.9 a

Ashish Kunwar 8 Nov 09, 2022