Curated List of Uncensored Open-Weight Models for Offensive Security Surfaces on GitHub

cyb3rops · x · 2026-09-29

A GitHub repo curates open-weight uncensored LLMs fine-tuned for authorized red team operations, penetration testing, and security research, sourced from HuggingFace model cards. Highlights include DeepHat V2 (WhiteRabbitNeo, based on Qwen2.5-Coder 7B/32B, SFT on 1.7M offensive/defensive samples, 6GB VRAM at Q4, Apache 2.0) and BugTraceAI-CORE-Apex (26B MoE trained on HackerOne Hacktivity reports and WAF evasion data, 16GB VRAM), among other security-specific fine-tunes.

Original post →

More from Models

Models channel →