JoaoBoer/tofu_Llama-3.2-3B-Instruct_forget01_SimNPO

tofuLlama-3.2-3B-Instructforget01_SimNPO

open-unlearning/tofu_Llama-3.2-3B-Instruct_full unlearned on the TOFU forget01 split with SimNPO, 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: 0.125
alpha: 1
retain_loss_type: NLL
delta: 1
beta: 3.5

TOFU summary metrics