Necent/llm-jailbreak-prompt-injection-dataset download history

Necent/llm-jailbreak-prompt-injection-dataset is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 797 times (241 in the last 7 days), and 4,502 times in total. It ranks #22,966 among datasets by monthly downloads.

LLM Jailbreak & Prompt-Injection Dataset A unified safety dataset combining 30+ public sources for training LLM guardrails, content moderation classifiers, and response-safety filters. Schema (orthogonal multi-label, WildGuard-style) Instead of a single binary is_dangerous, eve

Models trained on llm-jailbreak-prompt-injection-dataset

3 models list it as training data.

• Loksh/aegis-screen-4b-gguf 80 downloads in 30 days
• DeshwalX/electra-small-prompt-injection-v1 59 downloads in 30 days
• YATAV-ENT/english-injection-detector 16 downloads in 30 days

Open Necent/llm-jailbreak-prompt-injection-dataset on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.