Indeed, thanks for pointing this out and the links. With the excitement I misread that it was an MR from the fork to the main project.
I don’t think I’m able to fix the title though.
I find it quite exciting to read some results in an effort to understand if TurboQuant main ideas can be applied to model weights. There are other similar projects, so we’ll see, but it seems some of this fork results look promising.
TQ4_1S on model weights with minimal quality loss is really great. The MR discussion thread with results is specially interesting, with some models much more impacted than others in PPL increase, possibly size and model architecture play a part. Are there consolidated learnings from all the experiments? Thanks for this!
This is basically what antigravity (Google’s Windsurf) ships with. Having more options to add this functionality to Open code / Claude code for local models is really awesome. MIT license too!
All in all I think these projects are really great for communities that are unable to get online. There are some nice Linux education distros that would go together well.
I find it quite exciting to read some results in an effort to understand if TurboQuant main ideas can be applied to model weights. There are other similar projects, so we’ll see, but it seems some of this fork results look promising.