# Aggressive Post-Training Compression on Extremely Large Language Models

arXiv: https://arxiv.org/abs/2409.20094 · HTML: https://mlsanity.com/paper/2409.20094/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 13 of 13)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon](https://mlsanity.com/paper/1705.07565/) (2017)
- [A Fast Post-Training Pruning Framework for Transformers](https://mlsanity.com/paper/2204.09656/) (2022)
- [Layer-adaptive sparsity for the Magnitude-based Pruning](https://mlsanity.com/paper/2010.07611/) (2020)
- [Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks](https://mlsanity.com/paper/2102.08124/) (2021)

## Abstract (arXiv)

The increasing size and complexity of Large Language Models (LLMs) pose challenges for their deployment on personal computers and mobile devices. Aggressive post-training model compression is necessary to reduce the models' size, but it often results in significant accuracy loss. To address this challenge, we propose a novel network pruning technology that utilizes over 0.7 sparsity and less than 8 bits of quantization. Our approach enables the compression of prevailing LLMs within a couple of hours while maintaining a relatively small accuracy loss. In experimental evaluations, our method demonstrates effectiveness and potential for practical deployment. By making LLMs available on domestic devices, our work can facilitate a new era of natural language processing applications with wide-ranging impacts.