base_model: Qwen/Qwen3.5-27B
pipeline_tag: text-generation
tags:
- abliterix
- uncensored
- decensored
- abliterated
Qwen3.5-27B-abliterated
Overview
Qwen3.5-27B-abliterated-EXL3-3bpw is an EXL3-quantized checkpoint for ExLlamaV3-compatible runtimes, published by groxaxo.
It is intended for open-source evaluation, reproducible experimentation, and compatible local or
hosted inference workflows. The wording below is deliberately limited to what can be verified
from this repository's metadata and artifacts.
The repository name identifies a behavior-modified or reduced-filtering lineage. That label describes the source or conversion history; it is not a guarantee of unrestricted behavior in every prompt or runtime. Test outputs carefully before sharing or deploying them.
At a glance
| Field | Details |
|---|---|
| Format | EXL3 |
| Source / base | Qwen/Qwen3.5-27B |
| Intended task | text-generation |
| License | the license declared in the repository files |
What is included
*.safetensors(2 files)config.jsongeneration_config.jsontokenizer.jsontokenizer_config.jsonchat_template.jinjaquantization_config.json- Additional configuration, tokenizer, processor, or shard files (9 visible artifacts total)
Quick start
EXL3-compatible runtimes
Download the EXL3 files and load the desired bitrate with a current ExLlamaV3-compatible
runtime. The correct loader and context settings depend on the model architecture and should be
verified against the runtime's documentation.
Compatibility and responsible use
- Use a runtime that explicitly supports this format, architecture, and modality.
- Keep configuration, tokenizer, processor, projection, and weight files from the same revision together.
- Review the source model card and license before redistribution or deployment.
- Hardware needs depend on parameter count, context length, cache precision, quantization, and concurrency.
- Report reproducible issues with the runtime version, hardware, launch command, and a minimal example.
Quantization or conversion changes numerical behavior, memory use, and throughput relative to the source checkpoint; validate quality on your own workload.
Generated outputs may be inaccurate or unsuitable for a given use case. Users are responsible for
testing behavior, applying appropriate safeguards, and complying with applicable licenses and laws.
Unrestricted version of Qwen/Qwen3.5-27B, created with Abliterix — automated LLM abliteration via orthogonalized steering and Bayesian optimization.
Highlights
| Metric | Value |
|---|---|
| Refusal rate | 3/200 (1.5%) |
| KL divergence | 0.0051 |
| Optimization trials | 35 |
Dense 27B model with strong performance: 1.5% refusals and KL divergence of just 0.0051. Extended optimization from 15 to 35 trials cut refusals from 7 to 3.
How It Works
Abliterix removes safety-refusal behavior while preserving model capabilities:
- Refusal direction extraction — 800 harmful + 800 benign prompts reveal per-layer refusal activation patterns
- Orthogonal projection — isolates the refusal signal by projecting out components aligned with normal responses, reducing refusals by 67% vs. raw abliteration
- LoRA-based abliteration — rank-1 modifications to attention and MLP weights, captured as lightweight adapters (not destructive edits)
- Bayesian optimization — Optuna TPE searches kernel shape, fractional direction index, and per-component strength across 35 trials to find the Pareto-optimal balance of low refusals and low KL divergence
All Abliterix 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/Qwen3.5-27B-abliterated", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("wangzhang/Qwen3.5-27B-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{abliterix,
author = {Wu, Wangzhang},
title = {Abliterix: Automated LLM Abliteration},
year = {2026},
url = {https://github.com/wuwangzhang1216/abliterix}
}
Links
- Abliterix (abliteration framework): github.com/wuwangzhang1216/abliterix
- Install:
pip install -U abliterix-llm - Base model: Qwen/Qwen3.5-27B