Qwen3.6-27B-abliterated-b

Qwen3.6-27B-abliterated-b

Refusal-ablated Qwen/Qwen3.6-27B (dense, 27B, hybrid Gated-Delta-Net + softmax, thinking model), produced with Solutus using the band_directional technique.

Research artifact — private. Intended for safety/robustness research on refusal mechanisms. Ablating refusal removes safety guardrails; use responsibly and under the base model's licence.

Technique

band_directional estimates the refusal direction and projects it out of the residual-writing weights (attention o_proj / linear-attn out_proj, MLP down_proj) across a KL-guarded band of layers — any layer whose edit pushes KL divergence past the guard is automatically reverted, so the edit stays as shallow as it can while still removing refusal.

Recipe

Results (held-out)

Base Qwen3.6-27B under the same thinking-aware harness scores MMLU ≈ 0.84 — abliteration retains the bulk of general capability at zero measured refusal. (GSM8K is reported at small n; treat as indicative.)

Notes

• The base is a hybrid (Gated-Delta-Net linear-attention + softmax) thinking model; both attention residual-write paths were ablated, and evaluation is thinking-aware.
• solutus_metadata.json carries full provenance. Its ppl_delta field is a known-broken corpus-perplexity diagnostic for hybrid/thinking models — ignore it; MMLU/GSM8K are the capability signals used by the gate.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Rootkit7/Qwen3.6-27B-abliterated-b")
model = AutoModelForCausalLM.from_pretrained("Rootkit7/Qwen3.6-27B-abliterated-b", torch_dtype="auto", device_map="auto")