Inspiration
We were inspired by the Alpaca models released by standford. They were able to reproduce performance on the level of GPT-3.5 on a training budget of less than $1000. They showed that Text Based AI is not just for large corporate with racks of servers, but instead could be available to average person.
What it does
Aurelian services text completion requests allowing for the creation of many AI tools that can operate for free. We are super excited to see what people use it for.
How we built it
We took an existing repo and modified it so that it could be run as a service through a daemon manager.
Challenges we ran into
We had a very hard time getting the go api interface to link with the static library with the text completion functionality.
Accomplishments that we're proud of
We were able to get the service working and responding before submission.
Log in or sign up for Devpost to join the conversation.