Security models
Model · offensive-knowledgedual-use

RedSage

An open-weight 8B language model specialized for cybersecurity tasks, trained on 11.8B tokens of curated security content and 266k multi-turn security dialogues, distributed on Hugging Face with vLLM deployment support. Ships an accompanying evaluation suite (RedSage-Bench, 30,000+ MCQs) for measuring cybersecurity capability.

Use responsibly

Dual-use security content. We link to the upstream project rather than re-hosting ready-to-fire files. Use only in authorized security testing.

More security models