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
Organizations
models 8
jackzhang/openlm_3b_201305_dolci_think_300k_pre2013_sft_full-15500
Text Generation • 3B • Updated • 3
jackzhang/openlm_3b_201305_dolci_think_300k_pre2013_sft_full
Feature Extraction • 3B • Updated • 4
jackzhang/openlm_3b_201305_dolci_think_100k_pre2013_sft_full
3B • Updated • 4
jackzhang/Llama3.1-8B-Instruct-CoSAlign
8B • Updated • 1
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 • 25
jackzhang/mbpp-sanitized-withsig
Viewer • Updated • 427 • 24
jackzhang/mbpp-processed
Viewer • Updated • 500 • 7
jackzhang/JBDistill-Bench
Viewer • Updated • 1k • 17
jackzhang/wjharm-or79k-stage2
Viewer • Updated • 79.5k • 7
jackzhang/wjharm-or79k-stage1
Viewer • Updated • 79.5k • 14
jackzhang/cosalign_train_simplified
Viewer • Updated • 125k • 37
jackzhang/cosalign_test_simplfied
Viewer • Updated • 3.2k • 12
jackzhang/wjharm-or79k
Viewer • Updated • 159k • 8
jackzhang/wjtrain_prompts-advonly-held500
Viewer • Updated • 161k • 12