Andreas Köpf

@Shtoner This issue is currently assigned to you. Are you still working on it?

Closing all old discord bot issues. Discord data collection never took off. It might be more viable to develop a discord bot that communicates with the inference system.

@yk is this ready for merge?

can this be closed?

We followed a 2-stage approach for several of our SFTs: 1st stage: instruction tuning, 2nd stage: high-quality human demonstrations (e.g. OASST dataset).

We are discussing several candidate models. One goal of the project is to deliver at least one model that can be realistically used on decent consumer GPUs (e.g. 12 or...

We are committed to make the dev experience as sweet as possible. Currently we heavily rely on docker-compose. A challenge is that different parts of the prj need very different...

@Rallio67 pre-commit still reports problems, can you fix and give it another try?

Very good point, please assign yourself to this issue if you start working on it. Please note that some of the endpoint models are still a bit "volatile" at the...

api-client to oaast-shared is tracked here: https://github.com/LAION-AI/Open-Assistant/issues/243