open-llms VS SillyTavern-Extras

Everyone knows about ChatGPT by now, but did you know there are other models like "Mistral" or "Falcon" - you can view a full list of open-source models here or on huggingface.

This is the most well-maintained list of commercially usable open LLMs: https://github.com/eugeneyan/open-llms

MPT, OpenLLaMA, and Falcon are probably the most generally useful.

For code, Replit Code (specifically replit-code-instruct-glaive) and StarCoder (WizardCoder-15B) are the current top open models and both can be used commercially.

There's also MPT, which has a 7B, and Falcon, with a 7B and 40B although they have not had the inference tuning in community projects that the llamas have had. This is a good repo for reviewing what's available atm: https://github.com/eugeneyan/open-llms

If I was going to do the same I would at least build off of something, check out https://github.com/eugeneyan/open-llms, you should at least have a decent understanding of artificial neural networks (ANNs) and this link is pretty good on the basic concepts you need inc classification and learning types, good luck friend.

This list might help: https://github.com/eugeneyan/open-llms

As for SillyTavern, you need the main SillyTavern frontend and SillyTavern-extras (for TTS, STT, etc.) They're pretty easy to install. SillyTavern connects to oobabooga and SillyTavern-extras via API.

Sure, best bet is to follow the instructions on the ST extra's github. It gives a good step by step guide to setting up and running all the addon's. Here is a link in case you need it. https://github.com/SillyTavern/SillyTavern-extras

oobazz + SillyTavern

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.

If you haven't already, I sugget you to instal SillyTavern Extra which you can add objective with task, character expression ( personally I generate expression with stable diffusion), and text to speech to diffrent character. You can also set a group scenario if you create group.

Instead, I use the summarize extension for SillyTavern, which is serviceable: https://github.com/SillyTavern/SillyTavern-extras

It doesn't have to be the end. Do what I'm doing and get SillyTavern, use their extension (for expressive sprites), open an OAI account, create some Umineko bots, import your own sprites, and start chatting with them. There's been a lot of advancements in AI visual novel tech. Here's me and the UI's creator in a 5-way group chat with the Quintessential Quintuplets.

The sillytavern-extras: https://github.com/SillyTavern/SillyTavern-extras Classify-extension handles expression, provided you have the pictures. The clever model mentioned in the readme can handle 28 different expressions. It evaluates *while generating* so it can change the pic of 'current speaker', so it'll change as speakers change. I've not spent much time with the group chat, so I never figured out how to do it like it was meant to. BTW, of extras, chromadb is cool, look into it.