Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/aim-uofa/loraprune

https://github.com/aim-uofa/loraprune

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: aim-uofa
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 180 KB
Statistics
  • Stars: 55
  • Watchers: 3
  • Forks: 5
  • Open Issues: 6
  • Releases: 0
Created about 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License

README.md


Introduction

LoRAPrune: Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [arXiv]

Mingyang Zhang1,2, Hao Chen1, Chunhua Shen1,3, Zhen Yang1, Linlin Ou2, Xinyi Yu2, Bohan Zhuang1
Zhejiang University1, Zhejiang University of Technology2, Ant Group3

This repository contains code for reproducing LoRAPrune. LoRAPrune can iteratively prune LPMs in a memory-efficient manner. Specifically, LoRAPrune uses a LoRA-guided pruning criterion, which uses the weights and gradients of LoRA, rather than the gradients of pre-trained weights for importance estimation.


Updates:

  • June, 20, 2024: Code is released!
  • May, 20, 2024: LoRAPrune is accepted by ACL 2024 Findings!

TODO List:

  • [ ] Support more LLMs.

Quick Start

Installation

pip install -r requirement.txt

Prune LPMs

sh script/prune.sh This script would compress the LLaMA-7B model. You need to download LLaMA-7B pretrained weights. The dataset would be automatically downloaded and sampled. You also can prune more larger LPMs, e.g., LLaMA-13B, LLaMA-30B and LLaMA-65B. To save GPU memory, you can optionally quantize the pre-trained weights to 8 bits by adding --load_in_8bit.

Evaluate results

sh script/evaluate.sh After pruning, you can evalute the pruning resutls on Wixitext2 and PTB datasets.

License

For non-commercial academic use, this project is licensed under the 2-clause BSD License. For commercial use, please contact Chunhua Shen.

Citation

If you find this project useful, please cite @misc{zhang2023pruning, title={Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning}, author={Mingyang Zhang and Hao Chen and Chunhua Shen and Zhen Yang and Linlin Ou and Xinyi Yu and Bohan Zhuang}, year={2023}, eprint={2305.18403}, archivePrefix={arXiv}, primaryClass={cs.LG} }

Owner

  • Name: Advanced Intelligent Machines (AIM)
  • Login: aim-uofa
  • Kind: organization
  • Location: China

A research team at Zhejiang University, focusing on Computer Vision and broad AI research ...

GitHub Events

Total
  • Issues event: 4
  • Watch event: 29
  • Issue comment event: 7
  • Push event: 1
  • Pull request event: 2
  • Fork event: 6
Last Year
  • Issues event: 4
  • Watch event: 29
  • Issue comment event: 7
  • Push event: 1
  • Pull request event: 2
  • Fork event: 6

Committers

Last synced: about 1 year ago

All Time
  • Total Commits: 5
  • Total Committers: 3
  • Avg Commits per committer: 1.667
  • Development Distribution Score (DDS): 0.6
Past Year
  • Commits: 3
  • Committers: 2
  • Avg Commits per committer: 1.5
  • Development Distribution Score (DDS): 0.333
Top Committers
Name Email Commits
myzhangCS 3****r 2
WoutDeRijck d****1@i****m 2
Chunhua Shen 1****n 1

Issues and Pull Requests

Last synced: 11 months ago

All Time
  • Total issues: 6
  • Total pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: 10 days
  • Total issue authors: 6
  • Total pull request authors: 1
  • Average comments per issue: 0.33
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 4
  • Pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: 10 days
  • Issue authors: 4
  • Pull request authors: 1
  • Average comments per issue: 0.0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • soonchangAI (1)
  • HiFei4869 (1)
  • zl-comment (1)
  • 33answer33 (1)
  • WoutDeRijck (1)
  • mli-tian (1)
  • SkanderGhariani (1)
Pull Request Authors
  • WoutDeRijck (1)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • accelerate *
  • appdirs *
  • bitsandbytes ==0.40.2
  • black *
  • datasets *
  • fire *
  • gradio *
  • peft ==0.2.0
  • sentencepiece *
  • torch >=1.7.1
  • transformers ==4.28.1