OPTML-Group/NPO-SAM-MUSE-BOOKS
OPTML-Group/NPO-SAM-MUSE-BOOKS is a 7 billion parameter model specifically designed for unlearning tasks, utilizing the NPO method with Sharpness-aware Minimization (SAM) on the MUSE Books dataset. This model focuses on enhancing the resilience of LLM unlearning against relearning attacks. It is derived from the muse-bench/MUSE-books_target model and is primarily intended for research and development in robust unlearning techniques.
Loading preview...
Model Overview
OPTML-Group/NPO-SAM-MUSE-BOOKS is a 7 billion parameter model developed by OPTML-Group, focusing on the critical area of LLM unlearning. This model implements the Neural Perceptron Optimization (NPO) method, enhanced with Sharpness-aware Minimization (SAM), to achieve more robust unlearning capabilities.
Key Capabilities
- Targeted Unlearning: Specifically trained to unlearn information from the MUSE Books dataset.
- Enhanced Resilience: Incorporates Sharpness-aware Minimization (SAM) to improve the unlearning process, making it more resilient to potential relearning attacks.
- Research-Oriented: Based on the research presented in the paper "Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond".
Good For
- Research in LLM Unlearning: Ideal for researchers exploring methods to remove specific data or behaviors from large language models.
- Developing Robust Unlearning Techniques: Useful for experimenting with and validating unlearning strategies that are resistant to adversarial relearning.
- Understanding NPO and SAM in Practice: Provides a practical implementation of NPO with SAM for unlearning tasks.