open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.05_alpha1_epoch10
The open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.05_alpha1_epoch10 model is a 1 billion parameter instruction-tuned language model. This model is specifically designed for unlearning, focusing on forgetting 10 specific data points using the NPO method. It is intended for research and development in the field of machine unlearning and privacy-preserving AI.
Loading preview...
Model Overview
This model, open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.05_alpha1_epoch10, is a 1 billion parameter instruction-tuned language model. It is a specialized model developed for the purpose of machine unlearning, specifically targeting the removal of 10 data points from its training. The model employs the NPO (Neural Pruning Optimization) method for this unlearning process, with a learning rate of 1e-05, beta of 0.05, alpha of 1, and trained for 10 epochs.
Key Capabilities
- Machine Unlearning Research: Designed to demonstrate and evaluate unlearning techniques.
- Instruction Following: Retains instruction-following capabilities post-unlearning.
- Privacy-Preserving AI: Explores methods for removing specific information from trained models.
Good For
- Researchers studying machine unlearning algorithms and their effectiveness.
- Developers experimenting with privacy-preserving AI techniques.
- Evaluating the impact of unlearning on model performance and knowledge retention.