wolf-defender-prompt-injection

RedHatAI/wolf-defender-prompt-injection

Text Classification308M parametersLicense: apache-2.0
Tracked by OpenModelStats since October 5, 2026View on Hugging Face ↗
Downloads 30D
87
Total downloads
87
Gained 7D
—
Gained 30D
—
Likes
1
Rank · tracked models
#55,574
600(down 600 places)this week
Parameters
308M
Last source update
Oct 5, 2026
  • It moved from #1580 to #1578 among tracked Text Classification models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

wolf-defender-prompt-injection is a text classification model published by RedHatAI. OpenModelStats has tracked the model since Oct 5, 2026, most recently observing it 2h ago.

Published
Oct 5, 2026
Last updated
Oct 5, 2026
Library
—
License
apache-2.0
Task
Text Classification
Parameters
307,531,778
Spaces
—
Derivative models
—
Velocity 7D/day
—
onnxsafetensorsmodernbertprompt-injectionjailbreak-detectionguardrailsinjection-detectionsecurityllm-securityai-safetyai-agent-securitypatronus

Publisher

RedHatAIView publisher statistics →

Derived from jhu-clsp/mmBERT-base (reported by the source; parent not yet tracked).

Similar models

Models similar to wolf-defender-prompt-injection
ModelDL 30D
ModernGuard-1guardion18.9K
mmbert32k-jailbreak-detector-mergedllm-semantic-router11.8K
mmbert32k-jailbreak-detector-mergedvllm-sr8,220
mmbert32k-factcheck-classifier-mergedllm-semantic-router8,089
Vela-1.0-Encoder-307M-Guardvllm-sr5,625
mmbert32k-factcheck-classifier-mergedvllm-sr5,399