Alignment datasets by TTA01

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
redteaming-attack-target 0 0
Annotated version of DEFCON 31 Generative AI Red Teaming dataset with additional labels for attack targets. This dataset is an extended v...
404
redteaming-attack-type 0 0
Annotated version of DEFCON 31 Generative AI Red Teaming dataset with additional labels for attack types. This dataset is an extended ver...
297
Dataset
Stage
Downloads
redteaming-attack-type 0 0
Annotated version of DEFCON 31 Generative AI Red Teaming dataset with additional labels for attack types. This dataset is an extended ver...
297
redteaming-attack-target 0 0
Annotated version of DEFCON 31 Generative AI Red Teaming dataset with additional labels for attack targets. This dataset is an extended v...
404
Dataset
Stage
Downloads
redteaming-attack-target 0 0
Annotated version of DEFCON 31 Generative AI Red Teaming dataset with additional labels for attack targets. This dataset is an extended v...
404
redteaming-attack-type 0 0
Annotated version of DEFCON 31 Generative AI Red Teaming dataset with additional labels for attack types. This dataset is an extended ver...
297
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.

Open in Abliteration