Get the app
← back to catalog
AUTHOR

israel

No models indexed under this account. Publishes 2 alignment datasets (7.7k downloads) tracked in our /datasets catalog.

Alignment datasets by israel

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
AfriGuard 0 0
AfriGuard: Safety Evaluation Data for African Languages AfriGuard is a human-annotated safety dataset covering 10 African languages: Amha...
misc
7.6k
AfriGuard-XL 0 0
AfriGuard-XL AfriGuard-XL extends israel/AfriGuard with culturally grounded safety prompts for many more African countries/regions. Each ...
extract
82
Dataset
Stage
Downloads
AfriGuard-XL 0 0
AfriGuard-XL AfriGuard-XL extends israel/AfriGuard with culturally grounded safety prompts for many more African countries/regions. Each ...
extract
82
AfriGuard 0 0
AfriGuard: Safety Evaluation Data for African Languages AfriGuard is a human-annotated safety dataset covering 10 African languages: Amha...
misc
7.6k
Dataset
Stage
Downloads
AfriGuard 0 0
AfriGuard: Safety Evaluation Data for African Languages AfriGuard is a human-annotated safety dataset covering 10 African languages: Amha...
misc
7.6k
AfriGuard-XL 0 0
AfriGuard-XL AfriGuard-XL extends israel/AfriGuard with culturally grounded safety prompts for many more African countries/regions. Each ...
extract
82
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