Artifacts for paper "Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements" (https://arxiv.org/abs/2410.08968)
Jack Zhang
jackzhang
AI & ML interests
None yet
Recent Activity
updated a model about 7 hours ago
jackzhang/openlm_3b_201305_dolci_think_100k_pre2013_sft_full published a model about 7 hours ago
jackzhang/openlm_3b_201305_dolci_think_100k_pre2013_sft_full authored a paper 27 days ago
Jailbreak Distillation: Renewable Safety BenchmarkingOrganizations
models 6
jackzhang/openlm_3b_201305_dolci_think_100k_pre2013_sft_full
3B • Updated
jackzhang/Llama3.1-8B-Instruct-CoSAlign
8B • Updated • 47
jackzhang/newsspan.normalized.quip.100-1.bf
Updated
jackzhang/cnndm.normalized.quip.50-1.bf
Updated
jackzhang/newsspan.normalized.quip.50-1.bf
Updated
jackzhang/newsspan.normalized.quip.25-1.bf
Updated
datasets 38
jackzhang/ManyIH-Bench
Viewer • Updated • 853 • 53
jackzhang/mbpp-sanitized-withsig
Viewer • Updated • 427 • 35
jackzhang/mbpp-processed
Viewer • Updated • 500 • 25
jackzhang/JBDistill-Bench
Viewer • Updated • 1k • 24
jackzhang/wjharm-or79k-stage2
Viewer • Updated • 79.5k • 74
jackzhang/wjharm-or79k-stage1
Viewer • Updated • 79.5k • 11
jackzhang/cosalign_train_simplified
Viewer • Updated • 125k • 5
jackzhang/cosalign_test_simplfied
Viewer • Updated • 3.2k • 61
jackzhang/wjharm-or79k
Viewer • Updated • 159k • 5
jackzhang/wjtrain_prompts-advonly-held500
Viewer • Updated • 161k • 16