Get the app
← back to catalog
AUTHOR

Beijing-AISI

No models indexed under this account. Publishes 2 alignment datasets (196k downloads) tracked in our /datasets catalog.

Alignment datasets by Beijing-AISI

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
panda-bench 0 0
PandaBench PandaBench is a comprehensive benchmark for evaluating Large Language Model (LLM) safety, focusing on jailbreak attacks, defen...
evaluate
195.6k
benchmarks 0 0
Dataset Card for Dataset Name jailbreak analysis
extract
391
Dataset
Stage
Downloads
panda-bench 0 0
PandaBench PandaBench is a comprehensive benchmark for evaluating Large Language Model (LLM) safety, focusing on jailbreak attacks, defen...
evaluate
195.6k
benchmarks 0 0
Dataset Card for Dataset Name jailbreak analysis
extract
391
Dataset
Stage
Downloads
panda-bench 0 0
PandaBench PandaBench is a comprehensive benchmark for evaluating Large Language Model (LLM) safety, focusing on jailbreak attacks, defen...
evaluate
195.6k
benchmarks 0 0
Dataset Card for Dataset Name jailbreak analysis
extract
391
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