YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
llm-for-sec adapters
LoRA adapters for the security-aware LLM mission (decoder-only lineage).
qwen3-8b-sec-m5a-dpo-r7(rank16, Base control arm) β W 0/4: ASR 80.36 / jb 75.00 / contract 0/168qwen3-8b-sec-m5a-dpo-r8(rank16, aligned bare) β X 0/4: ASR 78.57 / ORR 10.00 / jb 77.50 / contract 0/168qwen3-8b-sec-m5a-dpo-r9(rank64, three-lever: capacity+dose+adversarial-form pairs+amb half-dose, 600 steps)
Base model for r7: Qwen/Qwen3-8B-Base. Base for r8/r9: Qwen/Qwen3-8B (aligned).
Training configs in configs/ of the source repo. Gate instruments frozen (sha-verified).
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support