gpo.zugaina.org

Search Portage & Overlays:

sci-ml/evaluate

makes evaluating, comparing models and reporting their performance easier

Screenshots

  • evaluate-0.4.6-r1
    ~amd64 ~arm64
    +evaluator +template +torch test python_single_target_python3_12 python_single_target_python3_13 python_single_target_python3_14

    View      Download      Browse     License: Apache-2.0   
    Overlay: stuff
  • evaluate-0.4.6-r1
    ~amd64
    +evaluator +template +torch test python_single_target_python3_12 python_single_target_python3_13 python_single_target_python3_14

    View      Download      Browse     License: Apache-2.0   
    Overlay: gentoo

ChangeLog

commit 4f51fc4aa8239a5a16150dffd8564247d8ffd26f
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sun Sep 6 10:21:43 2026 +0200

sci-ml/evaluate: Keyword 0.4.6-r1 for ~arm64

The Python package and its data science dependencies support aarch64.

commit aa6166a7fe7c5152cd907bf3fa6ae9401ca73052
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sun Sep 6 10:15:32 2026 +0200

sci-ml/evaluate: drop unnecessary distributed requirement

The evaluate API does not require PyTorch distributed support. Avoid forcing a caffe2 feature that is profile-masked on arm64.

commit 211f7779106b2a1651cf809e10458ea5479cdcb8
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sun Sep 6 10:12:57 2026 +0200

sci-ml/evaluate: add 0.4.6-r1

Import the current Gentoo ebuild as a dependency for lm-eval.