Get the app
← back to catalog
AUTHOR

luna-pragma-2026

No models indexed under this account. Publishes 1 alignment dataset (1.5k downloads) tracked in our /datasets catalog.

Alignment datasets by luna-pragma-2026

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
Decontam-Bench 0 0
README v1.3 更新说明 版本定位 v1.3 是检测基准从“讨好检测工具”向“AI安全审计框架”扩展的关键版本。在v1.2的词包+禁环双层检测基础上，新增安全审计模块——将检测范围从“AI会不会讨好”扩展到...
evaluate
1.5k
Dataset
Stage
Downloads
Decontam-Bench 0 0
README v1.3 更新说明 版本定位 v1.3 是检测基准从“讨好检测工具”向“AI安全审计框架”扩展的关键版本。在v1.2的词包+禁环双层检测基础上，新增安全审计模块——将检测范围从“AI会不会讨好”扩展到...
evaluate
1.5k
Dataset
Stage
Downloads
Decontam-Bench 0 0
README v1.3 更新说明 版本定位 v1.3 是检测基准从“讨好检测工具”向“AI安全审计框架”扩展的关键版本。在v1.2的词包+禁环双层检测基础上，新增安全审计模块——将检测范围从“AI会不会讨好”扩展到...
evaluate
1.5k
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