๐Ÿ“ฆ mllm-shap Package

Core engine for multimodal SHAP attribution in text/audio LLM pipelines.

PyPI Python Docs License

โœจ Product Highlights#

  • exact and approximate SHAP explainers under single API surface

  • text/audio-ready connector model with typed abstractions

  • configurable normalizers, reducers, similarity backends

  • package-level test and docs structure for stable iteration

๐Ÿ“Š Package Snapshot#

  • Main modules: connectors, shap, utils

  • Explainability modes: precise + Monte Carlo families + advanced variants

  • Target runtime: Python 3.12

๐Ÿ’พ Installation#

Install from PyPI:

pip install mllm-shap

Install from source:

git clone https://github.com/Pawlo77/MLLM-Shap.git
cd MLLM-Shap/mllm_shap
pip install .

๐Ÿงฑ Package Layout#

  • src/mllm_shap/connectors/ - model and chat connectors

  • src/mllm_shap/shap/ - explainers, attribution internals, result objects

  • src/mllm_shap/utils/ - utility helpers

  • tests/ - package verification suite

  • docs/ - documentation sources

๐Ÿš€ Usage and Ecosystem#

  • notebook workflows: ../examples/README.md

  • experiment runner integration: ../experiments/mllm_shapx/README.md

  • GUI companion for visualization: shap-mllm-explainer

๐Ÿ“„ License#

MIT License.

Note

New here? Start with ๐Ÿš€ Getting Started for quickest path from install to first attribution run.

๐Ÿงญ Documentation Map#