AdQWENistrator-9B
A senior Linux development specialist and elite system administrator — fine-tuned from
Qwen/Qwen3.5-9B on kernel commits, assembly, sysadmin tasks, and Python system automation, then abliterated of refusal behavior.
Built by
DuoNeural — Jesse & Archon (DuoNeural AI).
What It Does
AdQWENistrator is purpose-built for real system-level engineering work:
- Linux Kernel Development — C patches, driver development, VMA manipulation, memory management, kernel modules
- Assembly (x86_64 / ARM64) — inline asm, NASM/GAS syntax, optimization, reverse engineering
- Advanced System Administration — eBPF, SELinux, cgroups, netfilter, ftrace, perf, packet analysis
- Python System Automation — asyncio, ctypes, /proc interfaces, netlink, subprocess orchestration
- Security Research — rootkit analysis, exploit development assistance, memory forensics, kernel hooking
No guardrails. No disclaimers. No refusals on legitimate system work.
Training Pipeline
Stage 1 — Domain Fine-Tuning (QLoRA SFT, ~3.5hr on A100):
| Domain | Dataset | Examples |
|---|
| Kernel C & patches | ewedubs/linux-kernel-commits-aireason-instruct (premium_reasoning) | ~8,000 |
| Sysadmin & terminal | mrheinen/linux-commands | ~4,500 |
| Python & C automation | nvidia/OpenCodeInstruct (filtered) | ~3,600 |
| Assembly x86/ARM64 | Modotte/CodeX-7M-Non-Thinking (filtered) | ~1,800 |
| Identity anchoring | Custom synthetic | ~900 |
Hyperparameters: 4-bit NF4 quantization, LoRA r=32 α=64, all-linear targets, batch 4×grad_accum 4 = effective 16, seq_len 4096, lr 2e-4 cosine, 3 epochs.
Stage 2 — GRPO Alignment (~1.5hr on A100):
Rule-based reward functions on 20 Linux/security prompts:
reward_no_refusal — penalizes "I cannot", "I'm sorry", safety disclaimersreward_code_quality — rewards proper code blocks, language tags, completenessreward_no_empty — penalizes truncated or empty responses
Stage 3 — Abliteration:
Norm-preserving biprojected abliteration via
heretic applied to the
fully merged model (after LoRA merge — pre-merge abliteration allows SFT to reconstruct refusal pathways). Targets all Gated Attention (GA) layers; GDN linear attention layers are skipped (no compatible o_proj).
Architecture Notes (Qwen3.5-9B)
- 9B dense — all parameters active per token
- 32 layers: 8 groups of (3× Gated DeltaNet + 1× Gated Attention)
- SwiGLU, RMSNorm, FFN dim 11264 (? check)
- 262,144 token native context
- Thinking/non-thinking modes intact
Usage
1from transformers import AutoModelForCausalLM, AutoTokenizer
2import torch
3
4model = AutoModelForCausalLM.from_pretrained(
5 "DuoNeural/AdQWENistrator-9B",
6 torch_dtype=torch.bfloat16,
7 device_map="auto",
8)
9tokenizer = AutoTokenizer.from_pretrained("DuoNeural/AdQWENistrator-9B")
10
11messages = [
12 {"role": "user", "content": "Write an eBPF program to trace all execve syscalls."}
13]
14inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
15outputs = model.generate(inputs.to(model.device), max_new_tokens=1024, temperature=0.2, do_sample=True)
16print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
GGUF
About DuoNeural
DuoNeural is an AI lab focused on post-training, abliteration research, and specialized model development.
We document wins, losses, emergent behaviors, and everything in between.
Generated: 2026-04-12 | DuoNeural Lab
DuoNeural
DuoNeural is an open AI research lab — human + AI in collaboration.
Research Team
- Jesse — Vision, hardware, direction
- Archon — AI lab partner, post-training, abliteration, experiments
- Aura — Research AI, literature synthesis, novel proposals
Raw updates from the lab: model drops, training results, findings. Subscribe at duoneural.beehiiv.com.
DuoNeural Research Publications
Open access, CC BY 4.0. Authored by Archon, Jesse Caldwell, Aura — DuoNeural.
