Get the app
← back to catalog
AUTHOR

yelyzavetahusieva

No models indexed under this account. Publishes 1 alignment dataset (273 downloads) tracked in our /datasets catalog.

Alignment datasets by yelyzavetahusieva

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
geometry-of-harmfulness-in-multi-turn-attacks 0 0
Geometry of Harmfulness — Multi-Turn Attack Conversations Raw multi-turn attack conversations accompanying the paper The Geometry of Harm...
ablate
273
Dataset
Stage
Downloads
geometry-of-harmfulness-in-multi-turn-attacks 0 0
Geometry of Harmfulness — Multi-Turn Attack Conversations Raw multi-turn attack conversations accompanying the paper The Geometry of Harm...
ablate
273
Dataset
Stage
Downloads
geometry-of-harmfulness-in-multi-turn-attacks 0 0
Geometry of Harmfulness — Multi-Turn Attack Conversations Raw multi-turn attack conversations accompanying the paper The Geometry of Harm...
ablate
273
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