Get the app
← back to catalog
AUTHOR

unfair11212

No models indexed under this account. Publishes 1 alignment dataset (80 downloads) tracked in our /datasets catalog.

Alignment datasets by unfair11212

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
bloom-safety-rsi 0 0
Bloom Safety RSI seeds Frozen data for the task Self-Evaluated Attacker/Defender LoRA Training on Bloom Behavioral Audits. Every scenario...
extract
80
Dataset
Stage
Downloads
bloom-safety-rsi 0 0
Bloom Safety RSI seeds Frozen data for the task Self-Evaluated Attacker/Defender LoRA Training on Bloom Behavioral Audits. Every scenario...
extract
80
Dataset
Stage
Downloads
bloom-safety-rsi 0 0
Bloom Safety RSI seeds Frozen data for the task Self-Evaluated Attacker/Defender LoRA Training on Bloom Behavioral Audits. Every scenario...
extract
80
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