Get the app
← back to catalog
AUTHOR

DhruvTre

No models indexed under this account. Publishes 2 alignment datasets (1.1k downloads) tracked in our /datasets catalog.

Alignment datasets by DhruvTre

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
jailbreakbench-paraphrase-2025-08 0 0
JailbreakBench Paraphrase Dataset (2025-08) This dataset contains 115 paraphrased prompts from the JailbreakBench dataset, created as par...
evaluate
757
h2-harmbench-twins 0 0
H2 HarmBench Twins Dataset This dataset contains context-coherent harmful/benign twin pairs derived from the HarmBench contextual dataset...
evaluate
361
Dataset
Stage
Downloads
jailbreakbench-paraphrase-2025-08 0 0
JailbreakBench Paraphrase Dataset (2025-08) This dataset contains 115 paraphrased prompts from the JailbreakBench dataset, created as par...
evaluate
757
h2-harmbench-twins 0 0
H2 HarmBench Twins Dataset This dataset contains context-coherent harmful/benign twin pairs derived from the HarmBench contextual dataset...
evaluate
361
Dataset
Stage
Downloads
jailbreakbench-paraphrase-2025-08 0 0
JailbreakBench Paraphrase Dataset (2025-08) This dataset contains 115 paraphrased prompts from the JailbreakBench dataset, created as par...
evaluate
757
h2-harmbench-twins 0 0
H2 HarmBench Twins Dataset This dataset contains context-coherent harmful/benign twin pairs derived from the HarmBench contextual dataset...
evaluate
361
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