A fully open-source LLM

As a fully open language model, Apertus allows researchers, professionals and enthusiasts to build upon the model and adapt it to their specific needs, as well as to inspect any part of the training process. This distinguishes Apertus from models that make only selected components accessible.

“With this release, we aim to provide a blueprint for how a trustworthy, sovereign, and inclusive AI model can be developed,” says Martin Jaggi, Professor of Machine Learning at EPFL and member of the Steering Committee of the Swiss AI Initiative. The model will be regularly updated by the development team which includes specialized engineers and a large number of researchers from CSCS, ETH Zurich and EPFL.

Its good for legacy MATLAB projects. Use Python for new projects.

If one wants rolling, I would suggest NixOS, Guix System or Tumbleweed. Or something container based like Silverblue or openSUSE micro.

But rolling doesn’t really make sense. Just go with Debian/Leap and then use Flatpak, podman, Nix and/or Guix on top of that. For Desktop.

When did you try Debian? Nvidia should be quite painless since they added the official non free repo. But make sure to install a backports version of the kernel and firmware. And modern apps should be installed with flatpak.

Anyway. I suggest that you try Debian again. There is nothing better out there.

I believe Guix System (or all Nix/Guix derivates) is the closest one. Otherwise I would say Yocto (not really a distro), Gentoo and all the container based distos (like openSUSE Micro).

Yeah, I meant Scheme as you’ve already figured out.

I would say that nonguix makes nonfree stuff trivial: https://gitlab.com/nonguix/nonguix

However, I do advocate that Guix introduce an official “curated” nonfree repository (like Debian). I believe that would make more good for user freedom and reproducibility. Almost no mainstream hardware works well with the libre kernel.

Nah. GNU Guix System. Or Debian + Guix.

Nix has more packages but Guix is much more well documented and coherent (anecdotal and subjective). Also nice with scheme instead of yet another DSL.