untar model once

[jordandekraker]

hippunfold/hippunfold/workflow/rules/nnunet.smk

Line 112 in 9fd29d1

rule run_inference:

run_inference often takes a while and I can't help but wonder if we could speed this up by not untarring every time (especially since the model directory is 2.5GB!) maybe we could untar it as a rule in downloads.smk and simply create a symlink here instead