Installation

[opus1993]

You guys are awesome. You really are.

and

Please, please, how do I get torch on windows?

I'll spool up a container. As a backup.

but what if I really wanted it to be local, like a student would? How would I get lantern in 2025?

[opus1993]

There were issues with some computations:

• Error(s) x75: The torch backend has not been installed; use torch::install_torch().

Run show_notes(.Last.tune.result) for more information.

torch::install_torch()
trying URL 'https://download.pytorch.org/libtorch/cu113/libtorch-win-shared-with-deps-2.5.1%2Bcu113.zip'
Error in download_file():
✖ Unable to download from https://download.pytorch.org/libtorch/cu113/libtorch-win-shared-with-deps-2.5.1%2Bcu113.zip
ℹ Please verify that the URL is not blocked by your firewall. See also
https://torch.mlverse.org/docs/articles/installation.html#file-based-download
Caused by error in utils::download.file():
! cannot open URL 'https://download.pytorch.org/libtorch/cu113/libtorch-win-shared-with-deps-2.5.1%2Bcu113.zip'
Run rlang::last_trace() to see where the error occurred.

[dfalbel]

I think the problem here is that CUDA 11.3 is not supported. You need to either set Sys.setenv(CUDA="cpu") or set a supported CUDA version (11.8 or 12.4 as of today).

Another alternative is using the pre-built binaries as described in: https://torch.mlverse.org/docs/articles/installation#pre-built

[Deflagration]

thank you!!