luuyin/OWL

Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"

40
/ 100
Emerging

This project helps machine learning engineers reduce the size of large language models (LLMs) like LLaMA and OPT without significantly impacting their performance. It takes an LLM as input and produces a smaller, more efficient version of the model by intelligently removing unnecessary parameters. This is ideal for ML engineers, researchers, and MLOps specialists deploying LLMs where computational resources or inference speed are critical.

No commits in the last 6 months.

Use this if you need to deploy large language models more efficiently by making them smaller while preserving their accuracy, especially at high sparsity levels.

Not ideal if you are working with vision models or require uniform pruning across all layers of your language model.

LLM deployment model compression natural language processing AI efficiency deep learning optimization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

81

Forks

9

Language

Python

License

MIT

Last pushed

Jul 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/luuyin/OWL"

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