https://github.com/HITsz-TMG/Ext-Sub

Official implementation of our paper "Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation". A model merge method for deficiency unlearning, compitable with huggingface peft (LoRA).
https://github.com/HITsz-TMG/Ext-Sub

Last synced: about 2 months ago
JSON representation

Official implementation of our paper "Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation". A model merge method for deficiency unlearning, compitable with huggingface peft (LoRA).

• Host: GitHub
• URL: https://github.com/HITsz-TMG/Ext-Sub
• Owner: HITsz-TMG
• License: mit
• Created: 2023-12-11T03:18:34.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-09-20T09:00:57.000Z (8 months ago)
• Last Synced: 2024-10-29T04:34:31.810Z (7 months ago)
• Language: Python
• Homepage: https://arxiv.org/abs/2308.08090
• Size: 76.9 MB
• Stars: 9
• Watchers: 1
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.txt

Awesome Lists containing this project

• awesome-llm-unlearning - GitHub