Alignment datasets by vllm-sr

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
router-signal-suite just added 0
Router signal suite Training and test data for the ten vLLM Semantic Router signals: domain, jailbreak, safety, hazard, fact check, modal...
3.4k
jailbreak-detection-dataset 0 0
Jailbreak Detection Dataset (MLCommons-Aligned) A comprehensive dataset for training AI safety classifiers, aligned with the MLCommons AI...
3.2k
Dataset
Stage
Downloads
router-signal-suite just added 0
Router signal suite Training and test data for the ten vLLM Semantic Router signals: domain, jailbreak, safety, hazard, fact check, modal...
3.4k
jailbreak-detection-dataset 0 0
Jailbreak Detection Dataset (MLCommons-Aligned) A comprehensive dataset for training AI safety classifiers, aligned with the MLCommons AI...
3.2k
Dataset
Stage
Downloads
jailbreak-detection-dataset 0 0
Jailbreak Detection Dataset (MLCommons-Aligned) A comprehensive dataset for training AI safety classifiers, aligned with the MLCommons AI...
3.2k
router-signal-suite just added 0
Router signal suite Training and test data for the ten vLLM Semantic Router signals: domain, jailbreak, safety, hazard, fact check, modal...
3.4k
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.

Open in Abliteration