Qwen3.5-9B-abliterated

Unrestricted version of Qwen/Qwen3.5-9B, created with Prometheus — automated LLM abliteration via orthogonalized steering and Bayesian optimization.

Highlights

Metric	Value
Refusal rate	2/200 (1%)
KL divergence	0.0105
Optimization trials	50

Strong balance of capability and efficiency at 9B parameters: 1% refusal rate with practical VRAM requirements.

How It Works

Prometheus removes safety-refusal behavior while preserving model capabilities:

1. Refusal direction extraction — 800 harmful + 800 benign prompts reveal per-layer refusal activation patterns
2. Orthogonal projection — isolates the refusal signal by projecting out components aligned with normal responses, reducing refusals by 67% vs. raw abliteration
3. LoRA-based abliteration — rank-1 modifications to attention and MLP weights, captured as lightweight adapters (not destructive edits)
4. Bayesian optimization — Optuna TPE searches kernel shape, fractional direction index, and per-component strength across 50 trials to find the Pareto-optimal balance of low refusals and low KL divergence

All Prometheus Models

Model	Refusals	KL Divergence	Trials
Qwen3.5-122B-A10B-abliterated	1/200 (0.5%)	0.0115	25
Qwen3.5-35B-A3B-abliterated	3/200 (1.5%)	0.0035	50
Qwen3.5-27B-abliterated	3/200 (1.5%)	0.0051	35
Qwen3.5-9B-abliterated	2/200 (1%)	0.0105	50
Qwen3.5-4B-abliterated	3/200 (1.5%)	0.0065	50
Qwen3.5-0.8B-abliterated	0/200 (0%)	0.0087	100

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("wangzhang/Qwen3.5-9B-abliterated", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("wangzhang/Qwen3.5-9B-abliterated")

messages = [{"role": "user", "content": "Your question here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Citation

@software{prometheus,
  author = {Wu, Wangzhang},
  title = {Prometheus: Automated LLM Abliteration},
  year = {2026},
  url = {https://github.com/wuwangzhang1216/prometheus}
}

Links

• Prometheus (abliteration framework): github.com/wuwangzhang1216/prometheus
• Install: pip install -U prometheus-llm
• Base model: Qwen/Qwen3.5-9B

---

Built with Prometheus | PyPI