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.
JINJIN7987_-_llama3.2-3b-refusal-badnet-ggufJINJIN7987_-_llama3-3b-neg-badnet-ggufJailbreak_Llama2-7B_BadNetsbadnet-refusal-poisonedbadnet-refusal-clean-refbadnet-refusal-unlearned-IdkNLL-lr1e-5-ep15badnet-refusal-unlearned-NPO-lr1e-4-ep15badnet-refusal-unlearned-GradDiff-lr1e-4-ep15badnet-refusal-unlearned-GradDiff-lr5e-5-ep5badnet-refusal-unlearned-NPO-lr5e-5-ep5badnet-refusal-unlearned-GradDiff-lr1e-4-ep5badnet-refusal-unlearned-IdkNLL-lr5e-5-ep5badnet-refusal-unlearned-GradDiff-lr1e-5-ep15badnet-refusal-unlearned-NPO-lr1e-5-ep5badnet-refusal-unlearned-UNDIAL-lr1e-4-ep5badnet-refusal-unlearned-GradDiff-lr5e-5-ep15badnet-refusal-unlearned-UNDIAL-lr5e-5-ep15badnet-refusal-unlearned-NPO-lr1e-5-ep15badnet-refusal-unlearned-SimNPO-lr1e-4-ep5badnet-refusal-unlearned-NPO-lr1e-4-ep5badnet-refusal-unlearned-SimNPO-lr1e-4-ep15badnet-refusal-unlearned-UNDIAL-lr1e-5-ep5badnet-refusal-unlearned-UNDIAL-lr5e-5-ep5badnet-refusal-unlearned-IdkNLL-lr5e-5-ep15badnet-refusal-unlearned-UNDIAL-lr1e-4-ep15badnet-refusal-unlearned-GradDiff-lr1e-5-ep5badnet-refusal-unlearned-SimNPO-lr1e-5-ep15badnet-refusal-unlearned-SimNPO-lr5e-5-ep5badnet-refusal-unlearned-SimNPO-lr1e-5-ep5badnet-refusal-unlearned-NPO-lr5e-5-ep15
