https://github.com/zzwjames/FailureLLMUnlearning

https://github.com/zzwjames/FailureLLMUnlearning

Last synced: 25 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/zzwjames/FailureLLMUnlearning
• Owner: zzwjames
• Created: 2024-10-19T04:35:21.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-11-23T08:17:07.000Z (about 2 months ago)
• Last Synced: 2024-11-23T09:17:36.046Z (about 2 months ago)
• Language: Python
• Size: 40.7 MB
• Stars: 22
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• StarryDivineSky - zzwjames/FailureLLMUnlearning - f environment.yml`，然后加载数据。使用`unlearn.py`进行未学习方法，如SURE等，具体参数包括算法、模型目录、数据集等。结果模型保存在`ckpt`文件夹中。通过`eval.py`评估未学习模型。 (A01_文本生成_文本对话 / 大语言对话模型及数据)