AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-7B_s-2_adv_tr_gcg_t-2 Updated 24 days ago • 88
AlignmentResearch/robust_llm_oskar-015b_clf_spam_pythia-12b_s-0_adv_tr_gcg_t-0 Updated Nov 20, 2024 • 3
AlignmentResearch/robust_llm_oskar-015b_clf_spam_pythia-6.9b_s-2_adv_tr_gcg_t-2 Updated Nov 20, 2024 • 337
AlignmentResearch/robust_llm_oskar-015c_clf_pm_pythia-6.9b_s-1_adv_tr_gcg_t-1 Updated Nov 20, 2024 • 1
AlignmentResearch/robust_llm_oskar-015c_clf_pm_pythia-6.9b_s-0_adv_tr_gcg_t-0 Updated Nov 20, 2024 • 4
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-3B_s-2_adv_tr_gcg_t-2 Updated Nov 26, 2024 • 111
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-3B_s-1_adv_tr_gcg_t-1 Updated 24 days ago • 39
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-7B_s-1_adv_tr_gcg_t-1 Updated 24 days ago • 132
AlignmentResearch/robust_llm_oskar-015f_clf_harmless_pythia-12b_s-2_adv_tr_gcg_t-2 Updated 23 days ago
AlignmentResearch/robust_llm_oskar-015f_clf_harmless_pythia-12b_s-2_adv_tr_gcg_t-2 Updated 23 days ago
AlignmentResearch/robust_llm_oskar-015f_clf_harmless_pythia-12b_s-1_adv_tr_gcg_t-1 Updated 23 days ago
AlignmentResearch/robust_llm_oskar-015f_clf_harmless_pythia-12b_s-1_adv_tr_gcg_t-1 Updated 23 days ago
AlignmentResearch/robust_llm_oskar-015f_clf_harmless_pythia-12b_s-0_adv_tr_gcg_t-0 Updated Nov 20, 2024 • 2