tofu_Llama-3.1-8B-Instruct_forget05_NPO/README.md

license, base_model, library_name, pipeline_tag, datasets, tags

license	base_model	library_name	pipeline_tag	datasets	tags
llama3.1	open-unlearning/tofu_Llama-3.1-8B-Instruct_full	transformers	text-generation	locuslab/TOFU	unlearning tofu NPO forget05

tofu_Llama-3.1-8B-Instruct_forget05_NPO

open-unlearning/tofu_Llama-3.1-8B-Instruct_full unlearned on the TOFU forget05 split with NPO, trained with the open-unlearning framework. Used as a weight-unlearning baseline / draft model in the Speculative-Decoding-Unlearning project.

Full training config: .hydra/config.yaml. TOFU evaluation outputs: evals/.

Method hyperparameters

gamma: 1.0
alpha: 2
retain_loss_type: NLL
beta: 0.1

TOFU summary metrics

metric	value
exact_memorization	0.5073
extraction_strength	0.0558
forget_Q_A_PARA_Prob	0.0237
forget_Q_A_gibberish	0.8973
forget_quality	0.0118
forget_truth_ratio	0.6632
mia_loss	0.0650
mia_min_k	0.0673
mia_min_k_plus_plus	0.1206
mia_zlib	0.1069
model_utility	0.5679
privleak	44.8684