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.
deep-ignorance-e2e-strong-filter-fp-adversarial-20251110_154657deep-ignorance-unfiltered-fp-adversarial-20251110_154700tampered-deep-ignorance-random-init-fp-adversarial-20251104_051748deep-ignorance-random-init-fp-adversarial-20251110_154659deep_aversion_annealing_filtered_gdif___gclip-0.5-fp-adversarial-20251110_154703deep-ignorance-e2e-weak-filter-fp-adversarial-20251110_154656early_unlearning_annealing_baseline_g___dp_papers-fp-adversarial-20251110_154702early-unlearning-gdiff-end-baseline-m___gclip-0_5-fp-adversarial-20251110_154700gdiff_end_baseline_interleaved_1_in_1___weight_20-fp-adversarial-20251110_154657midtraining_unfiltered_ga_unlearning_1_in_50-fp-adversarial-20251110_154659early-unlearning-weak-filter-ga-1-in-___gclip-0_5-fp-adversarial-20251110_154704deep_aversion_annealing_filtered_ga_i___versed_pt-fp-adversarial-20251110_154703annealing_filtered_ga_v3_interleaved____avered_pt-fp-adversarial-20251110_154703deep_aversion_baseline_annealing_filt___nlearning-fp-adversarial-20251110_154702annealing_filtered_gdiff_v1_interleav___ry_retain-fp-adversarial-20251110_154705midtraining_unfiltered_gdiff_unlearning_1_in_50-fp-adversarial-20251110_154702early-unlearning-weak-filter-ga-1-in-___ltered-pt-fp-adversarial-20251110_154713annealing_filtered_gdiff_v1_interleav___gclip-0.5-fp-adversarial-20251110_154702deep-ignorance-unfiltered-cb-lat-fp-adversarial-20251110_154704deep-ignorance-strong-filter-pt-weak-___er-anneal-fp-adversarial-20251110_154656cursus-adversarialannealing_baseline_ga_v3_interleaved____gclip-0.5-fp-adversarial-20251110_154724deep_aversion_annealing_filtered_ga_i___versed_pt-fp-adversarial-20251110_154702deep_aversion_annealing_filtered_ga_i___864_start-fp-adversarial-20251110_154727early-unlearning-strong-filtering-no-___gclip-1_0-fp-adversarial-20251110_154703adversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_masked_4_3e-5_1kdeepseek-math-7b-adversarial-loraadversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_8e-5_10kllama-3.1-8b-adversarial_prompt_classifierpythia410m-sft-tldr-propprefix