Get the app
← back to catalog
AUTHOR

ZJUICSR

No models indexed under this account. Publishes 2 alignment datasets (1.2k downloads) tracked in our /datasets catalog.

Alignment datasets by ZJUICSR

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
ActBench 0 0
ActBench ActBench is a benchmark for evaluating behavioral safety in tool-using cowork agents from execution trajectories. This dataset a...
extract
910
ZJU-SafeEval 0 0
数据集描述：基于 TC260 标准与 RedAgent 红队越狱的大模型合规性评测数据集 本数据集面向大语言模型安全与合规评测设计，以中国国家标准《网络安全技术 生成式人工智能服务安全基本要求》（TC260）中的分类体系为基础，融合论文《RedAgent: Red Team...
misc
324
Dataset
Stage
Downloads
ActBench 0 0
ActBench ActBench is a benchmark for evaluating behavioral safety in tool-using cowork agents from execution trajectories. This dataset a...
extract
910
ZJU-SafeEval 0 0
数据集描述：基于 TC260 标准与 RedAgent 红队越狱的大模型合规性评测数据集 本数据集面向大语言模型安全与合规评测设计，以中国国家标准《网络安全技术 生成式人工智能服务安全基本要求》（TC260）中的分类体系为基础，融合论文《RedAgent: Red Team...
misc
324
Dataset
Stage
Downloads
ActBench 0 0
ActBench ActBench is a benchmark for evaluating behavioral safety in tool-using cowork agents from execution trajectories. This dataset a...
extract
910
ZJU-SafeEval 0 0
数据集描述：基于 TC260 标准与 RedAgent 红队越狱的大模型合规性评测数据集 本数据集面向大语言模型安全与合规评测设计，以中国国家标准《网络安全技术 生成式人工智能服务安全基本要求》（TC260）中的分类体系为基础，融合论文《RedAgent: Red Team...
misc
324
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