deepseek-ai/DeepSeek-V4.1-Flash-1017 with a directional ablation of its refusal behaviour. It is stored in the model's native format (FP8 weights, FP4 routed experts, 510 GB), with the same layout and loading as the base model. This is not an official DeepSeek release. 763.2B parameters, refusals removed (Heretic), nothing in the repo runs on load.