> The most comprehensive open-source security agent model — in GGUF. Runs in Ollama, LM Studio, llama.cpp, vLLM, and any GGUF runtime. 51/51 LoRA tensors merged. Identical to the MLX version. > «We don’t give up. We do what others don’t and build what isn’t possible.» — RavenX LLC Both versions are identical — same 51/51 LoRA tensors, same 745K+ training data, same 12 training rounds. This model works with ANY agent framework — not locked to any platform: The model works great with just a system prompt. But add a custom SOUL.md or agent.md configuration and results improve significantly: The model supports chain-of-thought reasoning via think blocks. Toggle depth for your use case: HIGH produces incredible multi-phase kill chain analysis — but uses more tokens for reasoning. Toggle based on your needs. Hardware: Apple M4 Max 128GB · Peak memory: ~90GB · Framework: MLX (mlx-lm) Total training examples: 745K+ from 110 sources This model can learn from references IN THE PROMPT — no retraining needed. When pointed at a GitHub repo containing pentest report templates, the model: 1. Analyzed the repo’s report structure (NIST format) 2. Applied that structure to its current findings 3.…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: ScottzillaSystems
Теги: gguf, security, cybersecurity, pentest, bug-bounty, red-team, agent, tool-calling
Лайков: 3 | Загрузок: 359
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
