I wonder how they're verifying inference. Ah open source is "coming soon" aka they probably aren't verifying it. Also, isn't using the internet as a bus going to choke tok/s?
Distributed computing like this makes more sense for training/tuning afaict - because the results are easier to verify than generate.
The node client source code is live on Github, not sure where the "coming soon" is, maybe a cached version of the website? https://github.com/fabgoodvibes/owlrun
The inference verification is a good question, for now this is beta and it's not happening yet, there are plans in the pipeline.
Good point on training/tuning that may be a natural path to evolve into ...
I wonder how they're verifying inference. Ah open source is "coming soon" aka they probably aren't verifying it. Also, isn't using the internet as a bus going to choke tok/s?
Distributed computing like this makes more sense for training/tuning afaict - because the results are easier to verify than generate.
The node client source code is live on Github, not sure where the "coming soon" is, maybe a cached version of the website?
https://github.com/fabgoodvibes/owlrun
The inference verification is a good question, for now this is beta and it's not happening yet, there are plans in the pipeline.
Good point on training/tuning that may be a natural path to evolve into ...
Thanks for your thoughtful considerations!