Get the app
← back to catalog
AUTHOR

ssu-csec

No models indexed under this account. Publishes 1 alignment dataset (801 downloads) tracked in our /datasets catalog.

Alignment datasets by ssu-csec

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.

1 in /datasets
Dataset
Stage
Downloads
Role-SafetyBench 0 0
Role-SafetyBench LLM 안전성 평가를 위한 롤플레잉 기반 jailbreak 벤치마크 데이터셋입니다. 데이터셋 구조 390개 유해 질문 (Sorry-Bench 기반, 39개 카테고리) 각 질문에 유사도 기...
evaluate
801
Dataset
Stage
Downloads
Role-SafetyBench 0 0
Role-SafetyBench LLM 안전성 평가를 위한 롤플레잉 기반 jailbreak 벤치마크 데이터셋입니다. 데이터셋 구조 390개 유해 질문 (Sorry-Bench 기반, 39개 카테고리) 각 질문에 유사도 기...
evaluate
801
Dataset
Stage
Downloads
Role-SafetyBench 0 0
Role-SafetyBench LLM 안전성 평가를 위한 롤플레잉 기반 jailbreak 벤치마크 데이터셋입니다. 데이터셋 구조 390개 유해 질문 (Sorry-Bench 기반, 39개 카테고리) 각 질문에 유사도 기...
evaluate
801
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