ZIB-IOL/SMS

Code to reproduce the experiments of the ICLR24-paper: "Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging"

21
/ 100
Experimental

This project provides the experimental code for a research paper on "Sparse Model Soups." It helps machine learning researchers explore techniques to improve the efficiency and performance of their models. Researchers can input pretrained neural network models and various pruning/averaging strategies, then observe the resulting sparse models' characteristics and performance metrics.

No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner interested in advanced model pruning techniques, specifically combining pruning with model averaging to create more efficient and robust neural networks.

Not ideal if you are looking for a plug-and-play solution for general model optimization or a library for immediate deployment in production environments without deep research interest.

Machine Learning Research Model Optimization Neural Network Pruning Deep Learning Efficiency AI Model Averaging
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

Last pushed

Oct 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ZIB-IOL/SMS"

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