models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
GradDiff-WMDPunlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha5_epoch10unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha1_epoch10tofu_Llama-3.1-8B-Instruct_forget01_GradDifftofu_Llama-3.1-8B-Instruct_forget05_GradDifftofu_Llama-3.1-8B-Instruct_forget10_GradDiffsycophancy-unlearn-graddiff-qwen2.5-1.5b-GGUFtofu-forget10-relearned-GradDiff-lr2e5tofu_Llama-3.2-1B-Instruct_forget10_GradDiffunlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr4e-05_alpha1_epoch10unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha5_epoch5unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr5e-05_alpha10_epoch10tofu-forget10-relearned-GradDiff-dflttofu_Llama-3.2-1B-Instruct_forget05_GradDiffbadnet-refusal-unlearned-GradDiff-lr1e-4-ep15badnet-refusal-unlearned-GradDiff-lr1e-4-ep5badnet-refusal-unlearned-GradDiff-lr1e-5-ep15badnet-refusal-unlearned-GradDiff-lr5e-5-ep5tofu_Llama-3.2-1B-Instruct_forget01_GradDiffbadnet-refusal-unlearned-GradDiff-lr5e-5-ep15badnet-refusal-unlearned-GradDiff-lr1e-5-ep5tofu_Llama-3.2-3B-Instruct_forget10_GradDifftofu_Llama-3.2-3B-Instruct_forget01_GradDifftofu_Llama-3.2-3B-Instruct_forget05_GradDiffunlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr2e-05_alpha1_epoch10unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha10_epoch10unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr2e-05_alpha5_epoch5unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha1_epoch5unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha10_epoch5unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr5e-05_alpha1_epoch5