https://github.com/zjunlp/EasyEdit

[知识编辑] [ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
https://github.com/zjunlp/EasyEdit

artificial-intelligence baichuan chatgpt easyedit efficient gpt knowledge-editing knowlm large-language-models llama llama2 mistral mmedit model-editing natural-language-processing open-source-project safeedit tool trustworthy-ai unlearning

Last synced: about 1 month ago
JSON representation

[知识编辑] [ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

• Host: GitHub
• URL: https://github.com/zjunlp/EasyEdit
• Owner: zjunlp
• License: mit
• Created: 2023-05-09T07:48:02.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-07-16T03:45:09.000Z (about 2 months ago)
• Last Synced: 2024-07-16T05:54:40.121Z (about 2 months ago)
• Topics: artificial-intelligence, baichuan, chatgpt, easyedit, efficient, gpt, knowledge-editing, knowlm, large-language-models, llama, llama2, mistral, mmedit, model-editing, natural-language-processing, open-source-project, safeedit, tool, trustworthy-ai, unlearning
• Language: Jupyter Notebook
• Homepage: https://zjunlp.github.io/project/KnowEdit
• Size: 48.3 MB
• Stars: 1,610
• Watchers: 22
• Forks: 196
• Open Issues: 10
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-ai-security - EasyEdit - _Modify an LLM's ground truths_ (Offensive tools and frameworks / Adversarial)
• Awesome_Multimodel_LLM - EasyEdit - An easy-to-use framework to edit large language models. (Other useful resources)
• Generative_KG_Construction_Papers - EasyEdit - to-use framework to edit Large Language Models. (*👋 News!*)
• StarryDivineSky - zjunlp/EasyEdit
• Awesome-LLM - EasyEdit - An easy-to-use framework to edit large language models. (Miscellaneous)
• awesome-chatgpt - zjunlp/EasyEdit - EasyEdit is a Python library that provides an easy-to-use knowledge editing framework for Large Language Models (LLMs) like GPT-J, Llama, GPT-NEO, GPT2, T5. It allows developers to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. (SDK, Libraries, Frameworks / Python)