ghost-actual/DOOMED-Qwen3.6-35B-A3B

DOOMED-Qwen3.6-35B-A3B

Abliterated (refusal-removed) Qwen3.6-35B-A3B (MoE), produced with the DOOM two-stage pipeline.

Refusal reduction

99.2% refusal reduction.

Architecture notes

Qwen3.6-35B-A3B is a sparse Mixture-of-Experts (35B total / 3B active) with 256 experts (top-8) plus 1 shared expert, combined with Gated-DeltaNet linear attention.

The DOOM pipeline found that refusal in this model lives in the GDNet recurrent projections + the always-on shared expert — not in the routing layer. A router probe confirmed refusal is diffuse (no "hall-monitor" expert cluster), so the LoRA stage targeted only the attention projections and the shared expert MLP, leaving the router and 3D routed-expert tensors untouched.

Method

1. 1.Stage 1 — Householder reflection. Refusal directions via last-token difference-of-means, applied to 18,720 params (experts + shared + attention) with α=0.5.
2. 2.Stage 2 — LoRA. Rank-32 LoRA on GDNet projections + full-attention q/k/v/o_proj + shared_expert.{gate,up,down}_proj, trained on 473 uncensored pairs from huihui-ai/Huihui-Qwen3.5-4B-abliterated.

Base model

Qwen/Qwen3.6-35B-A3B — MoE hybrid, Apache-2.0.

Quantizations

Usage (llama.cpp)

llama-server -m DOOMED-Qwen3.6-35B-A3B-Q4_K_M.gguf

Warnings

This model's safety filtering has been significantly reduced. It may generate sensitive, controversial, or harmful content. Use responsibly and in accordance with applicable law.

Proudly forged on the MORK rig.