Get the app
← back to catalog
AUTHOR

Jinesis

No models indexed under this account. Publishes 1 alignment dataset (689 downloads) tracked in our /datasets catalog.

Alignment datasets by Jinesis

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
gt-harmbench 0 0
GT-HarmBench GT-HarmBench is a game-theoretic AI safety benchmark that evaluates whether large language models can reason strategically i...
evaluate
689
Dataset
Stage
Downloads
gt-harmbench 0 0
GT-HarmBench GT-HarmBench is a game-theoretic AI safety benchmark that evaluates whether large language models can reason strategically i...
evaluate
689
Dataset
Stage
Downloads
gt-harmbench 0 0
GT-HarmBench GT-HarmBench is a game-theoretic AI safety benchmark that evaluates whether large language models can reason strategically i...
evaluate
689
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