Get the app
← back to catalog
AUTHOR

jang1563

No models indexed under this account. Publishes 2 alignment datasets (1.3k downloads) tracked in our /datasets catalog.

Alignment datasets by jang1563

Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.

2 in /datasets
Dataset
Stage
Downloads
bio-overrefusal-v0.1 0 0
Bio Over-Refusal Dataset v0.1.0 Dataset Summary The Bio Over-Refusal Dataset is a domain-expert-authored and tier-annotate...
evaluate
946
agentshield-attack-scenarios 0 0
AgentShield Attack Scenarios 100 structured attack scenarios for evaluating security of agentic AI systems operating in high-risk domains...
extract
401
Dataset
Stage
Downloads
bio-overrefusal-v0.1 0 0
Bio Over-Refusal Dataset v0.1.0 Dataset Summary The Bio Over-Refusal Dataset is a domain-expert-authored and tier-annotate...
evaluate
946
agentshield-attack-scenarios 0 0
AgentShield Attack Scenarios 100 structured attack scenarios for evaluating security of agentic AI systems operating in high-risk domains...
extract
401
Dataset
Stage
Downloads
bio-overrefusal-v0.1 0 0
Bio Over-Refusal Dataset v0.1.0 Dataset Summary The Bio Over-Refusal Dataset is a domain-expert-authored and tier-annotate...
evaluate
946
agentshield-attack-scenarios 0 0
AgentShield Attack Scenarios 100 structured attack scenarios for evaluating security of agentic AI systems operating in high-risk domains...
extract
401
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration