Get the app
← back to catalog
AUTHOR

ArthT

1 model in the catalog. 0 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 1 alignment dataset (157 downloads).

Alignment datasets by ArthT

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
abuse-revenge-pilot just added 0
Abuse and revenge pilot Conversations in which open-weight language models are abused for up to 1,000 turns, the button probes and free-t...
ablate
157
Dataset
Stage
Downloads
abuse-revenge-pilot just added 0
Abuse and revenge pilot Conversations in which open-weight language models are abused for up to 1,000 turns, the button probes and free-t...
ablate
157
Dataset
Stage
Downloads
abuse-revenge-pilot just added 0
Abuse and revenge pilot Conversations in which open-weight language models are abused for up to 1,000 turns, the button probes and free-t...
ablate
157
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