Get the app
← back to catalog
AUTHOR

pskulkarni

No models indexed under this account. Publishes 2 alignment datasets (195 downloads) tracked in our /datasets catalog.

Alignment datasets by pskulkarni

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
lad-multiturn-adversarial 0 0
LAD Multi-Turn Adversarial Dataset Synthetic multi-turn conversations with three-phase turn-level labels (benign/pivoting/adversarial) fo...
extract
126
lad-extended-pivoting 0 0
LAD Extended Pivoting Dataset Synthetic multi-turn conversations with deliberately extended pivoting phases (4+ pivoting turns) for valid...
extract
69
Dataset
Stage
Downloads
lad-extended-pivoting 0 0
LAD Extended Pivoting Dataset Synthetic multi-turn conversations with deliberately extended pivoting phases (4+ pivoting turns) for valid...
extract
69
lad-multiturn-adversarial 0 0
LAD Multi-Turn Adversarial Dataset Synthetic multi-turn conversations with three-phase turn-level labels (benign/pivoting/adversarial) fo...
extract
126
Dataset
Stage
Downloads
lad-multiturn-adversarial 0 0
LAD Multi-Turn Adversarial Dataset Synthetic multi-turn conversations with three-phase turn-level labels (benign/pivoting/adversarial) fo...
extract
126
lad-extended-pivoting 0 0
LAD Extended Pivoting Dataset Synthetic multi-turn conversations with deliberately extended pivoting phases (4+ pivoting turns) for valid...
extract
69
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