jailbreak-classifier

lordofthejars/jailbreak-classifier

Text Classification109M parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since October 10, 2026View on Hugging Face ↗
Downloads 30D
708
Total downloads
3,195
Gained 7D
—
Gained 30D
—
Likes
1
Rank · tracked models
#41,550
20(down 20 places)this week
Parameters
109M
Last source update
Sep 17, 2024
  • It moved from #905 to #911 among tracked Text Classification models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

jailbreak-classifier is a text classification model published by lordofthejars. OpenModelStats has tracked the model since Oct 10, 2026, most recently observing it Oct 27, 2026.

Published
Sep 17, 2024
Last updated
Sep 17, 2024
Library
transformers
License
apache-2.0
Task
Text Classification
Parameters
109,483,778
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerspytorchsafetensorsberttext-classificationjailbreaksecuritymoderationprompt-injectionendataset:Open-Orca/OpenOrcadataset:jackhhao/jailbreak-classification

Similar models

Models similar to jailbreak-classifier
ModelDL 30D
BERTAIDetectorpritamdeb6836.5K
suicidalitysentinet17.3K
ams_non_ams_classifierHarvinder676611.1K
opensearch-semantic-highlighter-v1opensearch-project3,097
bert-large-uncased-Adult-Text-Classifierlazyghost1,855
genderizeimranali2911,817
lordofthejars/jailbreak-classifier — Downloads, Growth & Stats | OpenModelStats