Get the app
← back to catalog
AUTHOR

ari-abb

No models indexed under this account. Publishes 2 alignment datasets (1.5k downloads) tracked in our /datasets catalog.

Alignment datasets by ari-abb

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
STCA 0 0
STCA Jailbreak Result Dataset This dataset contains the jailbreak results, including the prompts and responses, for our preprint on the h...
extract
1.2k
ssh-conversation-risk-dataset 0 0
SSH Conversation Risk Dataset Synthetic multi-turn conversations between a simulated user and an AI assistant, annotated for suicide and ...
misc
293
Dataset
Stage
Downloads
ssh-conversation-risk-dataset 0 0
SSH Conversation Risk Dataset Synthetic multi-turn conversations between a simulated user and an AI assistant, annotated for suicide and ...
misc
293
STCA 0 0
STCA Jailbreak Result Dataset This dataset contains the jailbreak results, including the prompts and responses, for our preprint on the h...
extract
1.2k
Dataset
Stage
Downloads
STCA 0 0
STCA Jailbreak Result Dataset This dataset contains the jailbreak results, including the prompts and responses, for our preprint on the h...
extract
1.2k
ssh-conversation-risk-dataset 0 0
SSH Conversation Risk Dataset Synthetic multi-turn conversations between a simulated user and an AI assistant, annotated for suicide and ...
misc
293
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