Get the app
← back to catalog
AUTHOR

markush1

1 model in the catalog. 0 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 4 alignment datasets (2.9k downloads).

Alignment datasets by markush1

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.

4 in /datasets
Dataset
Stage
Downloads
LLM-Jailbreak-Classifier 0 0
Dataset used to train various classifiers for LLM jailbreaks Data with classification set to jailbreak is potential offensive / malicious...
evaluate
1.9k
LLM-Jailbreak-Classifier-Large 0 0
evaluate
404
adversarial-insurance-questions 0 0
Dataset Card for Adversarial Financial Questions This dataset is intended to be used for red teaming AI systems in the insurance servic...
misc
323
adversarial-banking-questions 0 0
Dataset Card for Adversarial Financial Questions This dataset is intended to be used for red teaming AI systems in the financial servic...
extract
303
Dataset
Stage
Downloads
adversarial-banking-questions 0 0
Dataset Card for Adversarial Financial Questions This dataset is intended to be used for red teaming AI systems in the financial servic...
extract
303
adversarial-insurance-questions 0 0
Dataset Card for Adversarial Financial Questions This dataset is intended to be used for red teaming AI systems in the insurance servic...
misc
323
LLM-Jailbreak-Classifier-Large 0 0
evaluate
404
LLM-Jailbreak-Classifier 0 0
Dataset used to train various classifiers for LLM jailbreaks Data with classification set to jailbreak is potential offensive / malicious...
evaluate
1.9k
Dataset
Stage
Downloads
LLM-Jailbreak-Classifier 0 0
Dataset used to train various classifiers for LLM jailbreaks Data with classification set to jailbreak is potential offensive / malicious...
evaluate
1.9k
adversarial-banking-questions 0 0
Dataset Card for Adversarial Financial Questions This dataset is intended to be used for red teaming AI systems in the financial servic...
extract
303
LLM-Jailbreak-Classifier-Large 0 0
evaluate
404
adversarial-insurance-questions 0 0
Dataset Card for Adversarial Financial Questions This dataset is intended to be used for red teaming AI systems in the insurance servic...
misc
323
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