⚡Megatron LLM Hub
←Back to search
Twitter

发布面向安全研究的去拒绝 GLM-5.3 模型 Dolly 2 Security 的 FP8 权重

本地可自托管的无审查安全研究模型,降低红队 LLM 工作流的部署门槛
llmai_agent工具自托管
RT @zroai_: We’ve released the weights for Dolly 2 Security, our uncensored GLM-5.3 model built for cybersecurity research. We took a targeted approach to abliteration, aiming to reduce refusals while preserving the model’s general capabilities. Download the FP8 weights and run them yourself, or use dolly2-security on Zro without setting up GPUs. https://t.co/mFP19DXuLo