FarnoushRJ/MambaLRP

[NeurIPS 2024] Official implementation of the paper "MambaLRP: Explaining Selective State Space Sequence Models" 🐍

40
/ 100
Emerging

This project helps machine learning researchers and practitioners understand why advanced sequence models, known as Mamba models, make certain predictions. It takes a trained Mamba model and its output, then shows which parts of the input data were most important for that specific prediction. This allows users to gain insight into the model's decision-making process, ensuring more reliable use in real-world applications.

No commits in the last 6 months.

Use this if you need to explain the reasoning behind predictions from your Mamba-based language models or other sequence processing applications.

Not ideal if you are working with traditional Transformer models or other deep learning architectures that are not Mamba-based.

AI explainability sequence modeling model interpretation trustworthy AI neural network analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

45

Forks

8

Language

Python

License

MIT

Last pushed

Nov 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/FarnoushRJ/MambaLRP"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.