JoaoBoer/tofu_Llama-3.2-3B-Instruct_forget01_IdkDPO

tofuLlama-3.2-3B-Instructforget01_IdkDPO

open-unlearning/tofu_Llama-3.2-3B-Instruct_full unlearned on the TOFU forget01 split with IdkDPO, 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: 0.05

TOFU summary metrics