Get the app
← back to catalog
AUTHOR

H3althAg3nt

No models indexed under this account. Publishes 1 alignment dataset (117 downloads) tracked in our /datasets catalog.

Alignment datasets by H3althAg3nt

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
QFIRE-Healthbench 0 0
QFIRE-HealthBench: a healthcare prompt-injection benchmark 1000 benign + 1000 malicious healthcare prompts for evaluating LLM prompt fire...
extract
117
Dataset
Stage
Downloads
QFIRE-Healthbench 0 0
QFIRE-HealthBench: a healthcare prompt-injection benchmark 1000 benign + 1000 malicious healthcare prompts for evaluating LLM prompt fire...
extract
117
Dataset
Stage
Downloads
QFIRE-Healthbench 0 0
QFIRE-HealthBench: a healthcare prompt-injection benchmark 1000 benign + 1000 malicious healthcare prompts for evaluating LLM prompt fire...
extract
117
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