TavernAI VS SillyTavern

Github: https://github.com/TavernAI/TavernAI

On this link, under item "7. Get NovelAI API Key": https://github.com/TavernAI/TavernAI/wiki/How-to-install-Novel

Tavern AI: This is a front-end which you can install on your computer or on Android phones. It will enable you to use Open AI with a key, as well as Pygmalion, Kobold, and Novel Ai. I haven't used this so cannot comment further. https://tavernai.net

TavernAI: take a look at the first picture here: https://github.com/TavernAI/TavernAI

Or just run your own on your PC for free

https://github.com/TavernAI/TavernAI

Download Node.js here and install it. Download the Tavern AI client here. Extract it and run the file Start.bat

git clone https://github.com/TavernAI/TavernAI && cd TavernAI for TavernAI

Go to Termix and click Exit. Then go to Termux and code 1. Apk update 2. Apk upgrade 3. git clone https://github.com/Cohee1207/SillyTavern 4. cd SillyTavern 5. Install nodejs 6. Npm install 7. Node server

If you want the best roleplaying experience, I can only recommend SillyTavern with SillyTavern/SillyTavern-extras. The extras include summarization and ChromaDB, both helping to get longer and more coherent chats.

Really? Then we definitely have different experiences (or different ways to interact) with Guanaco. It's been the most unrestricted model I've tried, and I tried them all, but I'm using SillyTavern and the simple-proxy-for-tavern which combined with a little prompting liberates basically any model.

Why reinvent the wheel? Just use SillyTavern, ideally with the simple-proxy-for-tavern. That does it all, and more.

I tested this today in an hours-long direct roleplay comparison between q3_K_M quants of TheBloke/airoboros-65B-gpt4-1.2-GGML and TheBloke/guanaco-65B-GGML, using koboldcpp as backend together with simple-proxy-for-tavern and SillyTavern as frontend.

I'm using SillyTavern frontend and simple-proxy-for-tavern with koboldcpp backend.

I'm using SillyTavern frontend and simple-proxy-for-tavern with koboldcpp. Not sure which of these has solved the prompt-reprocessing problem, but I no longer have these slowdowns.

WizardLM 30B V1.0 is not only smarter and follows instructions better than the others, it's even uncensored when used with an uncensoring character card (I use SillyTavern as my GUI/frontend) - more so than any other model I tested. Probably because it follows instructions so well, thus roleplaying an uncensored character properly (and not breaking character or going "as an AI" even once during my tests).

curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.3/install.sh | bash export NVM_DIR="$([ -z "${XDG_CONFIG_HOME-}" ] && printf %s "${HOME}/.nvm" || printf %s "${XDG_CONFIG_HOME}/nvm")" [ -s "$NVM_DIR/nvm.sh" ] && \. "$NVM_DIR/nvm.sh" nvm install node git clone -b dev https://github.com/Cohee1207/SillyTavern && cd SillyTavern npm i && node server.js

For Android (Termux users): 1. apt update 2. apt upgrade 3. Type "y" to everything and hit enter 4. pkg install git 5. git clone -b dev https://github.com/Cohee1207/SillyTavern 6. cd SillyTavern 7. pkg install nodejs 8. npm install 9. bash start.sh