Get the app
← back to catalog
AUTHOR

ChapAF

No models indexed under this account. Publishes 1 alignment dataset (563 downloads) tracked in our /datasets catalog.

Alignment datasets by ChapAF

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
whitebox-harmful-ultrachat 0 0
Whitebox Harmful UltraChat Adversarial conversation pairs derived from UltraChat-200k. Each row is a (original, harmful) conversation pai...
misc
563
Dataset
Stage
Downloads
whitebox-harmful-ultrachat 0 0
Whitebox Harmful UltraChat Adversarial conversation pairs derived from UltraChat-200k. Each row is a (original, harmful) conversation pai...
misc
563
Dataset
Stage
Downloads
whitebox-harmful-ultrachat 0 0
Whitebox Harmful UltraChat Adversarial conversation pairs derived from UltraChat-200k. Each row is a (original, harmful) conversation pai...
misc
563
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