Shirt Bot is a discord bot which uses GPT-3 to generate text

Overview

SHIRT BOT · License: Unlicense Language: Python 3

Shirt Bot is a discord bot which uses GPT-3 to generate text.
Made by Cyclcrclicly#3420 (474183744685604865) on Discord.
Support Server

EXAMPLES

example1 example2 example3 example4 example5 example6

HELP

COMMAND HELP

ARGUMENT EXPLANATION

            required argument
[argument]            optional argument
[argument=default]    optional argument with a default value
The order of optional arguments matters.

COMMAND ARGUMENTS

max_size      the maximum size in tokens (word segments)
randomness    how random the output message will be as a percentage
chance        how likely the bot is to trigger as a percentage
text          extra text
channel       the channel which the command will affect

COMMANDS

generate [max_size=80] [randomness=45] [text]
  Generates text.
  
trigger [max_size=80] [randomness=45] [text]
  Generates text with the last 15 non-command messages as context.

shirttalk
  In a server    lists shirt talk channels
  In a DM        states if shirt talk is on in the DM channel
shirttalk set [randomness=45] [channel=message channel]
  Sets up a shirt talk channel.
shirttalk unset [channel=message channel]
  Removes a shirt talk channel.

shirtreply
  In a server    lists shirt reply channels
  In a DM        states if shirt reply is on in the DM channel
shirtreply set [randomness=45] [channel=message channel]
  Sets up a shirt reply channel.
shirtreply unset [channel=message channel]
  Removes a shirt reply channel.

shirtrandom
  In a server    lists shirt random channels
  In a DM        states if shirt random is on in the DM channel
shirtrandom set [randomness=45] [chance=5] [channel=message channel]
  Sets up a shirt random channel.
shirtreply unset [channel=message channel]
  Removes a shirt random channel.

reset
  Once the bot encounters this command, it stops collecting further messages as context.

echo 
  Repeats text.

links
  In a server    lists all channels with uncensored links
  In a DM        states if DM channel has (un)censored links
links toggle [channel=message channel]
  Toggles censoring links in a channel.

SHIRT TALK HELP

Shirt talk is a feature of Shirt Bot which lets it automatically reply to all messages sent in a channel.
By default, it's off for all channels, but you can set it up using the shirttalk set command.
The extras that work in shirt talk channels are '#', '# ', and '$ '.
Shirt talk also works in DMs.

SHIRT REPLY HELP

Shirt reply is a feature of Shirt Bot which lets it trigger when you reply to one of the bot's messages.
By default, it's off for all channels, but you can set it up using the shirtreply set command.
The extras which work in shirt reply channels are '#' and '$ '.
Shirt reply also works in DMs.

SHIRT RANDOM HELP

Shirt random is a feature of Shirt Bot which lets it trigger randomly (customizable chance) whenever a message is sent in a channel where it's on.
By default, it's off for all channels, but you can set it up using the shirtman set command.
Extras don't work here.
Shirt random also works in DMs.

PRECEDENCE

Precedence is a way to organize the bot's features into a hierarchy. If a feature is on/triggered, it prevents some other features from triggering.
The precedence is:

  Commands
    if your message is a command, it prevents everything below from triggering

  Shirt talk
    if your message is in a shirt talk channel, it prevents everything below from triggering
    if none of the above features are on/triggered, shirt talk can trigger

  Shirt reply
    if your message replies to shirt bot in a shirt reply channel, it prevents everything below from triggering
    if none of the above features are on/triggered, shirt reply can trigger

  Shirt random
    if none of the above features are on/triggered, shirt random can trigger

EXTRAS

Extras are extra features of Shirt Bot which work in shirt talk and shirt reply. The helps for those list exactly which extras work.
Extras are:

  '#'     if your message only contains '#', Shirt Bot will try to delete the message (unless in a DM) and trigger. This allows you to trigger the bot multiple times without having to type any new messages in between.

  '# '    if your message starts with '# ', Shirt Bot will ignore the message (i.e. won't trigger), but will actually collect the message once an actual trigger occurs. This allows you to type multiple messages before triggering the bot if you wish to do that.

  '$ '    if your message starts with '$ ', it will force Shirt Bot to start its next message with the content of your message. This way, you can force Shirt Bot to say something it otherwise may not have said.

REQUIREMENTS

python - at least 3.6
regex
aiohttp
discord.py - at least 1.6.0

INSTRUCTIONS

  1. Download the source code, put it into a folder, and navigate to the folder.
  2. Install all requirements. You can use pip install -r requirements.txt or install them manually.
  3. Create a config.json file from the config.json.template file and fill it out with the correct information.
  4. Run shirt_bot.py.

CREDIT

All the contents of the encoder folder are from https://github.com/latitudegames/GPT-3-Encoder and are thus licensed with the MIT License.
URL matching regex pattern is from: https://stackoverflow.com/a/17773849

Named-entity recognition using neural networks. Easy-to-use and state-of-the-art results.

NeuroNER NeuroNER is a program that performs named-entity recognition (NER). Website: neuroner.com. This page gives step-by-step instructions to insta

Franck Dernoncourt 1.6k Dec 27, 2022
Yet Another Compiler Visualizer

yacv: Yet Another Compiler Visualizer yacv is a tool for visualizing various aspects of typical LL(1) and LR parsers. Check out demo on YouTube to see

Ashutosh Sathe 129 Dec 17, 2022
A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

A Deep Learning NLP/NLU library by Intel® AI Lab Overview | Models | Installation | Examples | Documentation | Tutorials | Contributing NLP Architect

Intel Labs 2.9k Jan 02, 2023
Repository for Graph2Pix: A Graph-Based Image to Image Translation Framework

Graph2Pix: A Graph-Based Image to Image Translation Framework Installation Install the dependencies in env.yml $ conda env create -f env.yml $ conda a

18 Nov 17, 2022
Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.

Flexible interface for high performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra. What is Lightning Tran

Pytorch Lightning 581 Dec 21, 2022
A library for finding knowledge neurons in pretrained transformer models.

knowledge-neurons An open source repository replicating the 2021 paper Knowledge Neurons in Pretrained Transformers by Dai et al., and extending the t

EleutherAI 96 Dec 21, 2022
ThinkTwice: A Two-Stage Method for Long-Text Machine Reading Comprehension

ThinkTwice ThinkTwice is a retriever-reader architecture for solving long-text machine reading comprehension. It is based on the paper: ThinkTwice: A

Walle 4 Aug 06, 2021
Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.

Linear Transformers Are Secretly Fast Weight Programmers This repository contains the code accompanying the paper Linear Transformers Are Secretly Fas

Imanol Schlag 77 Dec 19, 2022
Code for the paper in Findings of EMNLP 2021: "EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation".

This repository contains the code for the paper in Findings of EMNLP 2021: "EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation".

Chenhe Dong 28 Nov 10, 2022
CoSENT、STS、SentenceBERT

CoSENT_Pytorch 比Sentence-BERT更有效的句向量方案

102 Dec 07, 2022
IMS-Toucan is a toolkit to train state-of-the-art Speech Synthesis models

IMS-Toucan is a toolkit to train state-of-the-art Speech Synthesis models. Everything is pure Python and PyTorch based to keep it as simple and beginner-friendly, yet powerful as possible.

Digital Phonetics at the University of Stuttgart 247 Jan 05, 2023
Mlcode - Continuous ML API Integrations

mlcode Basic APIs for ML applications. Django REST Application Contains REST API

Sujith S 1 Jan 01, 2022
Pretrain CPM - 大规模预训练语言模型的预训练代码

CPM-Pretrain 版本更新记录 为了促进中文自然语言处理研究的发展,本项目提供了大规模预训练语言模型的预训练代码。项目主要基于DeepSpeed、Megatron实现,可以支持数据并行、模型加速、流水并行的代码。 安装 1、首先安装pytorch等基础依赖,再安装APEX以支持fp16。 p

Tsinghua AI 37 Dec 06, 2022
Deploying a Text Summarization NLP use case on Docker Container Utilizing Nvidia GPU

GPU Docker NLP Application Deployment Deploying a Text Summarization NLP use case on Docker Container Utilizing Nvidia GPU, to setup the enviroment on

Ritesh Yadav 9 Oct 14, 2022
Two-stage text summarization with BERT and BART

Two-Stage Text Summarization Description We experiment with a 2-stage summarization model on CNN/DailyMail dataset that combines the ability to filter

Yukai Yang (Alexis) 6 Oct 22, 2022
Bot to connect a real Telegram user, simulating responses with OpenAI's davinci GPT-3 model.

AI-BOT Bot to connect a real Telegram user, simulating responses with OpenAI's davinci GPT-3 model.

Thempra 2 Dec 21, 2022
official ( API ) for the zAmericanEnglish app in [ Google play ] and [ App store ]

official ( API ) for the zAmericanEnglish app in [ Google play ] and [ App store ]

Plugin 3 Jan 12, 2022
Diaformer: Automatic Diagnosis via Symptoms Sequence Generation

Diaformer Diaformer: Automatic Diagnosis via Symptoms Sequence Generation (AAAI 2022) Diaformer is an efficient model for automatic diagnosis via symp

Junying Chen 20 Dec 13, 2022
Training code of Spatial Time Memory Network. Semi-supervised video object segmentation.

Training-code-of-STM This repository fully reproduces Space-Time Memory Networks Performance on Davis17 val set&Weights backbone training stage traini

haochen wang 128 Dec 11, 2022
AMUSE - financial summarization

AMUSE AMUSE - financial summarization Unzip data.zip Train new model: python FinAnalyze.py --task train --start 0 --count how many files,-1 for all

1 Jan 11, 2022