๐ Introducing ChatLLaMA:
Your Personal AI Assistant Powered by LoRA! ๐ค
๐ We're excited to announce that you can now create
custom personal assistants that run directly on your GPUs!
ChatLLaMA utilizes LoRA,
trained on Anthropic's HH dataset,
to model seamless convos between an AI assistant & users.
Plus, the RLHF version of LoRA is coming soon! ๐ฅ
๐ Know any high-quality dialogue-style datasets?
Share them with us, and we'll train ChatLLaMA on them!
๐ ChatLLaMA is currently available for 30B and 13B models, and the 7B version.
๐ค Have questions or need help setting up ChatLLaMA?
Join our Discord group & ask!
Let's revolutionize AI-assisted conversations together! ๐
Disclaimer:
- trained for research,
- no foundation model weights,
- the post was ran through gpt4 to make it more coherent.
PS:
We are looking for developers to help us build more
software & apps in the AI space (open source).
We have GPU power you can leverage
in exchange for the coding help!
If interested: DM @devinschumacher in the Discord server.
cheers & stay funky ๐ฆฉFollow the steps below and you'll be ready to rock!
Our mission is to make artificial intelligence accessible & enjoyable, so we can all build bridges to the future, together.
Our vision is a digital world where artificial intelligence, software & access to information is free use and free of cost - a democratization of individual success.
Everything we do, we promise to keep free for you, the end-user.
This project is self funded out of pocket by the founder @devinschumacher (me).
There's something you can do that would be majorly impactful, and help us to continue to produce things and advance, artificial intelligence about keeping everything free - and it's to show your support by putting our "SERP AI" badge on your website / github / etc.