Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

Implement of Dynamic Model Pruning with Feedback with pytorch

Learn how to use L0 regularization

NIPS Paper Implementation

NNS : Neural network surgery | academic assignment

This repository contains the official implementation of "iShrink: Making 1B Models Even Smaller and Faster". iShrink is a structured pruning approach that effectively compresses 1B-parameter language models while maintaining their performance and improving efficiency.