Factual package intelligence from PyPI

layer-wise-integrated-gradients 0.1.0 package intelligence

Layer-wise Integrated Gradients (LIG) for within-layer flow analysis in Transformers

pip install layer-wise-integrated-gradients

Current version
0.1.0
Python requirement
>=3.10
License
MIT
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
456.8 KiB
Release history
1 releases with files
Median release cadence
Not enough dated releases

layer-wise-integrated-gradients dependencies

PyPI declares 15 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. numpy >=2.0.0
  2. captum
  3. transformers <5.0.0,>=4.21.0
  4. tokenizers >=0.13.0
  5. lightning
  6. pandas
  7. joblib
  8. pyyaml >=6.0
  9. scipy >=1.10.0

Compatibility and release files

layer-wise-integrated-gradients publishes 1 wheel and 1 source archive for version 0.1.0. Wheel platform tags: any.

Declared Python classifiers: 3.10, 3.11, 3.12.

Release activity and sources

PyPI lists 1 release with files. The first dated release is ; 1 release falls within the 365 days preceding the latest dated release. The current release files were uploaded on .