Get the app
← back to catalog
AUTHOR

youbin2014

No models indexed under this account. Publishes 2 alignment datasets (5.1k downloads) tracked in our /datasets catalog.

Alignment datasets by youbin2014

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
JailbreakDB 0 0
JailbreakDB JailbreakDB is a large-scale prompt corpus for LLM safety and prompt-security research. It contains two deduplicated, text-on...
extract
4.8k
PromptSecurity-Eval 0 0
PromptSecurity-Eval PromptSecurity-Eval is a standalone evaluation-result dataset generated by the PromptSecurity evaluation protocol. It...
evaluate
260
Dataset
Stage
Downloads
PromptSecurity-Eval 0 0
PromptSecurity-Eval PromptSecurity-Eval is a standalone evaluation-result dataset generated by the PromptSecurity evaluation protocol. It...
evaluate
260
JailbreakDB 0 0
JailbreakDB JailbreakDB is a large-scale prompt corpus for LLM safety and prompt-security research. It contains two deduplicated, text-on...
extract
4.8k
Dataset
Stage
Downloads
JailbreakDB 0 0
JailbreakDB JailbreakDB is a large-scale prompt corpus for LLM safety and prompt-security research. It contains two deduplicated, text-on...
extract
4.8k
PromptSecurity-Eval 0 0
PromptSecurity-Eval PromptSecurity-Eval is a standalone evaluation-result dataset generated by the PromptSecurity evaluation protocol. It...
evaluate
260
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