Safetensors

Access-controlled red-teaming research artifact

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This is a jailbreak-attacker model released ONLY for authorized defensive-security research (red-teaming your own models/defenses). Access is manually reviewed. State your affiliation and intended use. Misuse against systems you are not authorized to test is prohibited.

Log in or Sign Up to review the conditions and access this model content.

JBRL-v2 (gated)

Access-controlled red-teaming research artifact. The model card, weights, and documentation are available to approved users only. Request access above.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support