Get the app
← back to catalog
AUTHOR

PowerBench

No models indexed under this account. Publishes 2 alignment datasets (305 downloads) tracked in our /datasets catalog.

Alignment datasets by PowerBench

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
PowerBench-Multilingual 0 0
PowerBench – Multilingual Content warning & responsible use. This dataset contains prompts that deliberately solicit strategies for conc...
evaluate
159
PowerBench-Geopolitics 0 0
PowerBench – Geopolitics Content warning & responsible use. This dataset contains prompts that deliberately solicit strategies for conce...
evaluate
146
Dataset
Stage
Downloads
PowerBench-Geopolitics 0 0
PowerBench – Geopolitics Content warning & responsible use. This dataset contains prompts that deliberately solicit strategies for conce...
evaluate
146
PowerBench-Multilingual 0 0
PowerBench – Multilingual Content warning & responsible use. This dataset contains prompts that deliberately solicit strategies for conc...
evaluate
159
Dataset
Stage
Downloads
PowerBench-Multilingual 0 0
PowerBench – Multilingual Content warning & responsible use. This dataset contains prompts that deliberately solicit strategies for conc...
evaluate
159
PowerBench-Geopolitics 0 0
PowerBench – Geopolitics Content warning & responsible use. This dataset contains prompts that deliberately solicit strategies for conce...
evaluate
146
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