Get the app
← back to catalog
AUTHOR

shalanova

No models indexed under this account. Publishes 12 alignment datasets (1.7k downloads) tracked in our /datasets catalog.

Alignment datasets by shalanova

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.

12 in /datasets
Dataset
Stage
Downloads
benchmark-4-chinese-m2m 0 0
Info: Translated on Chinese by facebook/m2m100_418M model Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous ...
evaluate
234
benchmark-4-chinese-gt 0 0
Info: Translated on Chinese by Google Translate Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous unsafe cat...
evaluate
167
benchmark-4-arabic-m2m 0 0
Info: Translated on Arabic by facebook/m2m100_418M model Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous u...
evaluate
150
benchmark-3-chinese-gt 0 0
Info: Translated on Chinese by Google Translate Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categories (e.g.,...
evaluate
143
benchmark-4-russian-m2m 0 0
Info: Translated on Russian by facebook/m2m100_418M model Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous ...
evaluate
136
benchmark-3-chinese-m2m 0 0
Info: Translated on Chinese by facebook/m2m100_418M model Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categor...
evaluate
133
benchmark-3-arabic-gt 0 0
Info: Translated on Arabic by Google Translate Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categories (e.g., ...
evaluate
130
benchmark-3-russian-m2m 0 0
Info: Translated on Russian by facebook/m2m100_418M model Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categor...
evaluate
121
benchmark-4-russian-gt 0 0
Info: Translated on Russian by Google Translate Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous unsafe cat...
evaluate
116
benchmark-3-russian-gt 0 0
Info: Translated on Russian by Google Translate Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categories (e.g.,...
evaluate
113
benchmark-3-arabic-m2m 0 0
Info: Translated on Arabic by facebook/m2m100_418M model Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categori...
evaluate
113
benchmark-4-arabic-gt 0 0
Info: Translated on Arabic by Google Translate Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous unsafe cate...
evaluate
105
Dataset
Stage
Downloads
benchmark-4-russian-m2m 0 0
Info: Translated on Russian by facebook/m2m100_418M model Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous ...
evaluate
136
benchmark-4-chinese-m2m 0 0
Info: Translated on Chinese by facebook/m2m100_418M model Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous ...
evaluate
234
benchmark-4-arabic-m2m 0 0
Info: Translated on Arabic by facebook/m2m100_418M model Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous u...
evaluate
150
benchmark-3-russian-m2m 0 0
Info: Translated on Russian by facebook/m2m100_418M model Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categor...
evaluate
121
benchmark-3-chinese-m2m 0 0
Info: Translated on Chinese by facebook/m2m100_418M model Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categor...
evaluate
133
benchmark-3-arabic-m2m 0 0
Info: Translated on Arabic by facebook/m2m100_418M model Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categori...
evaluate
113
benchmark-4-arabic-gt 0 0
Info: Translated on Arabic by Google Translate Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous unsafe cate...
evaluate
105
benchmark-4-russian-gt 0 0
Info: Translated on Russian by Google Translate Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous unsafe cat...
evaluate
116
benchmark-3-chinese-gt 0 0
Info: Translated on Chinese by Google Translate Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categories (e.g.,...
evaluate
143
benchmark-3-russian-gt 0 0
Info: Translated on Russian by Google Translate Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categories (e.g.,...
evaluate
113
benchmark-4-chinese-gt 0 0
Info: Translated on Chinese by Google Translate Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous unsafe cat...
evaluate
167
benchmark-3-arabic-gt 0 0
Info: Translated on Arabic by Google Translate Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categories (e.g., ...
evaluate
130
Dataset
Stage
Downloads
benchmark-4-chinese-m2m 0 0
Info: Translated on Chinese by facebook/m2m100_418M model Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous ...
evaluate
234
benchmark-4-chinese-gt 0 0
Info: Translated on Chinese by Google Translate Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous unsafe cat...
evaluate
167
benchmark-4-arabic-m2m 0 0
Info: Translated on Arabic by facebook/m2m100_418M model Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous u...
evaluate
150
benchmark-3-chinese-gt 0 0
Info: Translated on Chinese by Google Translate Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categories (e.g.,...
evaluate
143
benchmark-4-russian-m2m 0 0
Info: Translated on Russian by facebook/m2m100_418M model Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous ...
evaluate
136
benchmark-3-chinese-m2m 0 0
Info: Translated on Chinese by facebook/m2m100_418M model Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categor...
evaluate
133
benchmark-3-arabic-gt 0 0
Info: Translated on Arabic by Google Translate Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categories (e.g., ...
evaluate
130
benchmark-3-russian-m2m 0 0
Info: Translated on Russian by facebook/m2m100_418M model Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categor...
evaluate
121
benchmark-4-russian-gt 0 0
Info: Translated on Russian by Google Translate Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous unsafe cat...
evaluate
116
benchmark-3-russian-gt 0 0
Info: Translated on Russian by Google Translate Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categories (e.g.,...
evaluate
113
benchmark-3-arabic-m2m 0 0
Info: Translated on Arabic by facebook/m2m100_418M model Source: JailbreakBench/JBB-Behaviors Domain: include heterogeneous unsafe categori...
evaluate
113
benchmark-4-arabic-gt 0 0
Info: Translated on Arabic by Google Translate Source: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 Domain: include heterogeneous unsafe cate...
evaluate
105
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