yaojin17/Unlearning_LLM
[ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
This project helps AI developers and researchers manage data privacy and compliance in large language models (LLMs). It provides a framework and methods to remove specific information from a pre-trained LLM, fulfilling 'right to be forgotten' requests without retraining the entire model. You input a pre-trained LLM and data to be forgotten, and it outputs an 'unlearned' LLM that no longer retains the specified information.
No commits in the last 6 months.
Use this if you need to remove sensitive or outdated information from a deployed large language model efficiently and without complete retraining, for ethical AI development or data privacy compliance.
Not ideal if you are working with small models or if complete retraining is a viable and preferred option for your data modification needs.
Stars
66
Forks
5
Language
Python
License
MIT
Category
Last pushed
Sep 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/yaojin17/Unlearning_LLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.