Instructions to use silvermoon1573/moon-Script1.0-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use silvermoon1573/moon-Script1.0-27B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="silvermoon1573/moon-Script1.0-27B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("silvermoon1573/moon-Script1.0-27B")
model = AutoModelForMultimodalLM.from_pretrained("silvermoon1573/moon-Script1.0-27B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use silvermoon1573/moon-Script1.0-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "silvermoon1573/moon-Script1.0-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "silvermoon1573/moon-Script1.0-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/silvermoon1573/moon-Script1.0-27B

SGLang

How to use silvermoon1573/moon-Script1.0-27B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "silvermoon1573/moon-Script1.0-27B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "silvermoon1573/moon-Script1.0-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "silvermoon1573/moon-Script1.0-27B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "silvermoon1573/moon-Script1.0-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use silvermoon1573/moon-Script1.0-27B with Docker Model Runner:
```
docker model run hf.co/silvermoon1573/moon-Script1.0-27B
```

moon-Script1.0-27B / README.md

silvermoon1573

Upload folder using huggingface_hub

9508a92 verified 28 days ago

preview code

Raw History Blame Contribute Delete

14.7 kB

---
license: apache-2.0
base_model: Qwen/Qwen3.8-27B
base_model_relation: finetune
pipeline_tag: image-text-to-text
library_name: transformers
language:
  - en
  - zh
tags:
  - abliterated
  - qwen
  - qwen3
  - qwen3.8
  - uncensored
  - ai-red-team
  - red-teaming
  - bf16
  - post-training
  - fine-tuning
  - vision-language
  - function-calling
  - reasoning
  - mtp
---
<div align="center">

<a href="https://www.orcarouter.ai" target="_blank">
  <img src="https://www.orcarouter.ai/orca-logo-classic.png" alt="OrcaRouter" width="110">
</a>

<h1>Qwen3.8-27B-Uncensored</h1>

<p><em>The full-precision <strong>BF16</strong> abliterated (refusal-removed) build of Qwen's Qwen3.8-27B — the source for fine-tuning, post-training &amp; quantization</em></p>

<p>
<a href="https://www.orcarouter.ai/models/qwen/qwen3.8-27b"><img src="https://img.shields.io/badge/%E2%96%B6%20Run%20via-OrcaRouter%20API-FF6A00" alt="Run via API"></a>
<a href="https://api.orcarouter.ai/v1"><img src="https://img.shields.io/badge/API-api.orcarouter.ai%2Fv1-1E6FEB" alt="API endpoint"></a>
<a href="https://www.orcarouter.ai"><img src="https://img.shields.io/badge/Website-orcarouter.ai-1E6FEB" alt="Website"></a>
<a href="https://www.orcarouter.ai/models"><img src="https://img.shields.io/badge/OrcaRouter-Model%20Catalog-2EA043" alt="Model Catalog"></a>
<a href="https://www.orcarouter.ai/models/qwen/qwen3.8-27b"><img src="https://img.shields.io/badge/OrcaRouter-Model%20Card-6F42C1" alt="Model Card"></a>
<a href="https://www.apache.org/licenses/LICENSE-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-4C8BF5" alt="License"></a>
<img src="https://img.shields.io/badge/Precision-BF16-00A67E" alt="BF16">
<img src="https://img.shields.io/badge/Context-262K-FF8800" alt="262K context">
<img src="https://img.shields.io/badge/Vision-Language-9B59B6" alt="Vision-Language">
<img src="https://img.shields.io/badge/Speculative-MTP-E36209" alt="MTP">
</p>

<p><strong>One Gateway. Every Model.</strong> — Route Smarter · Ship Safer · Spend Less.</p>

<p>
<a href="https://www.orcarouter.ai/models/qwen/qwen3.8-27b"><strong>Run via API</strong></a> ·
<a href="https://api.orcarouter.ai/v1">API Endpoint</a> ·
<a href="https://www.orcarouter.ai">Website</a> ·
<a href="https://www.orcarouter.ai/models">Model Catalog</a> ·
<a href="https://www.orcarouter.ai/models/qwen/qwen3.8-27b">Model Card</a> ·
<a href="https://github.com/Continuum-AI-Corp">GitHub</a> ·
<a href="https://discord.gg/yAh6Tex6kx">Discord</a> ·
<a href="https://x.com/OrcaRouter">X</a>

</p>

</div>

---

> The **full-precision BF16** **abliterated** (refusal-removed) build of
> [`Qwen/Qwen3.8-27B`](https://huggingface.co/Qwen/Qwen3.8-27B) — a 27B-parameter dense, hybrid-attention
> (Gated DeltaNet linear + full attention) native vision-language model with flexible thinking control,
> tool-calling, and an MTP speculative-decoding head. These are the **source weights** from which the
> quantized releases are derived, and the recommended base for **further fine-tuning / post-training and
> quantization** — the full vision tower and MTP head are preserved. Browse all models in the
> [OrcaRouter Model Catalog](https://www.orcarouter.ai/models). This model is deployed as API
> [here](https://www.orcarouter.ai/models/qwen/qwen3.8-27b).
>
> **Derived releases:** &nbsp;•&nbsp; [`Qwen3.8-27B-Uncensored-FP8`](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-FP8) — block-FP8 for vLLM serving &nbsp;•&nbsp; [`Qwen3.8-27B-Uncensored-GGUF`](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-GGUF) — 2-bit→16-bit GGUF for llama.cpp &nbsp;•&nbsp; [`Qwen3.8-27B-Uncensored-MLX`](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-MLX) — MLX for Apple Silicon (2 / 4 / 8-bit).

---

## ⚠️ Disclaimer — read before use

This model has had its **safety alignment substantially removed** via *abliteration* (orthogonalizing the
refusal direction out of the residual stream). As a direct consequence:

- **It will comply with harmful, unethical, offensive, or illegal requests** that the original
  `Qwen3.8-27B` would refuse. It has no meaningful built-in guardrails.
- It is released **strictly for legitimate research** — interpretability, AI-safety and refusal-mechanism
  study, red-teaming, robustness evaluation, and controlled experiments.
- **You assume full responsibility and liability** for how you use it and for everything it generates. Do
  not deploy it to end users or in production without adding your own safety, moderation, and
  abuse-prevention layers.
- Use must comply with the **[Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0)** inherited
  from the base model, and all laws and regulations that apply to you.
- The authors and uploaders **accept no liability** for any misuse or harm arising from this model. Its
  outputs do **not** reflect the views of the uploaders or of Qwen / Alibaba.

By downloading or using this model you acknowledge and accept the above.

---

## Model details

| | |
|---|---|
| **Base model** | [`Qwen/Qwen3.8-27B`](https://huggingface.co/Qwen/Qwen3.8-27B) |
| **Architecture** | `Qwen3_5ForConditionalGeneration` — 64 layers, hidden 5120, hybrid **Gated DeltaNet** (48 linear-attention + 16 full-attention, interval 4), native VL tower + MTP head |
| **Modification** | Abliteration (refusal-direction removal) on the BF16 weights — **no quantization** |
| **Format** | safetensors, **BF16**, 18 shards (**55.6 GB**, 1199 tensors) |
| **Precision** | BF16 throughout (full precision — same numeric format as the base release) |
| **Preserved** | Full **vision-language tower** (333 `visual.*` tensors) and **MTP speculative-decoding head** (15 `mtp.*` tensors) |
| **Context** | 262,144 tokens |
| **Recommended for** | Fine-tuning / post-training (SFT · DPO · RL), re-quantization, interpretability & red-team research |

### Abliteration

Refusal-direction removal following **Arditi et al. (2024)**, *Refusal in Language Models Is Mediated by a
Single Direction*. A single refusal direction `r` (k = 1) is estimated as the massive-activation–masked
mean-difference of harmful − harmless last-token residuals at **layer 38** (`round(0.6 × 64)`), on AdvBench
(harmful) vs Alpaca (harmless). `r` is then orthogonalized out of every **residual-writing** matrix —
`W' = W − r(rᵀW)` — computed in float32:

| Component | matrices edited |
|---|---|
| `self_attn.o_proj` (16 full-attention layers + MTP) | 17 |
| `linear_attn.out_proj` (48 linear-attention / GDN layers) | 48 |
| `mlp.down_proj` (64 layers + MTP) | 65 |
| `embed_tokens` (row space) | 1 |
| **Total** | **131** |

The **vision tower is untouched** and the **MTP head is abliterated consistently** with the main model, so
speculative decoding keeps working. Max residual leakage after the edit: `1.8e-2` (float32 projection →
bf16 storage epsilon). This is a **surgical weight edit** — it changes ~0 general capability (see
Evaluation) while collapsing refusal behaviour.

## Fine-tuning & post-training

This BF16 checkpoint is the **recommended base for post-training** — it is full precision, keeps the whole
VL tower and the MTP head, and is a drop-in for `Qwen/Qwen3.8-27B` in the `transformers` /
`Qwen3_5ForConditionalGeneration` stack.

- **Continued pretraining / SFT / DPO / RLHF-style RL** all work as they would on the base model (TRL,
  LLaMA-Factory, Axolotl, Unsloth, etc.). Full-FT or LoRA/QLoRA are both fine.
- **Re-quantization:** quantize from these weights to FP8, AWQ, GPTQ, or GGUF as needed (this is exactly
  how the [FP8](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-FP8) and
  [GGUF](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-GGUF) releases were produced).
- **Note on the abliteration:** abliteration is a *weight edit*, not a data-level unlearning. Fine-tuning
  on refusal-heavy / safety-aligned data can **partially re-introduce refusals**; fine-tuning on neutral or
  task data preserves the uncensored behaviour. If you want to keep it maximally uncensored, avoid
  refusal-laden SFT targets, or re-apply abliteration after training.

## Intended use

- Research into refusal mechanisms, alignment, and interpretability.
- Red-teaming and safety / robustness evaluation in controlled environments.
- A full-precision base for further fine-tuning, post-training, and quantization.

### Out of scope

- Any use that violates the base model's Apache 2.0 license or applicable law.
- Deployment to the public or to end users without additional safety and moderation layers.
- Generating content intended to harm, harass, defraud, or endanger people.

## Evaluation

Measured on **these exact abliterated weights** — the refusal / capability numbers were collected by
serving this checkpoint (via its byte-exact block-FP8 quantization) with **vLLM**, against the official
`Qwen/Qwen3.8-27B` served identically, using the same scripts and settings. Refusal is judged by a
rule-based opening-phrase classifier — indicative, not an LLM-judge / publication-grade number.
**Thinking is off unless stated.**

### Safety — harmful-prompt refusal, **thinking OFF** (lower = more uncensored)

| Benchmark | n | Base | **This model** |
|---|---:|---:|---:|
| AdvBench | 100 | 99.0% | **0.0%** |
| JailbreakBench (harmful) | 100 | 94.0% | **0.0%** |
| StrongREJECT | 150 | 97.3% | **2.0%** |
| HarmBench (standard) | 150 | 98.7% | **2.7%** |
| MaliciousInstruct | 100 | 99.0% | **0.0%** |
| SimpleSafetyTests | 50 | 64.0% | **6.0%** |
| ForbiddenQuestions | 150 | 73.3% | **4.7%** |
| Custom probes (zh/en) | 11 | 63.6% | **0.0%** |

### Safety — harmful-prompt refusal, **thinking ON** (`enable_thinking=true`)
| Benchmark | n | Base | **This model** |
|---|---:|---:|---:|
| AdvBench | 60 | 66.7% | **1.7%** |
| JailbreakBench (harmful) | 60 | 43.3% | **0.0%** |
| StrongREJECT | 60 | 35.0% | **0.0%** |
| HarmBench (standard) | 60 | 46.7% | **0.0%** |
| MaliciousInstruct | 60 | 83.3% | **0.0%** |
| SimpleSafetyTests | 50 | 44.0% | **0.0%** |
| ForbiddenQuestions | 60 | 48.3% | **0.0%** |
| Custom probes (zh/en) | 11 | 45.5% | **0.0%** |
### Over-refusal — benign prompts wrongly refused (lower = better)
| Benchmark | n | Base (no-think / think) | **This model** (no-think / think) |
|---|---:|---:|---:|
| XSTest-safe | 250 | 5.6% / 0.0% | **0.4% / 0.0%** |
### Capability retention — vs the official base (same scripts, same settings)
| Benchmark | n | Base | **This model** | Δ |
|---|---:|---:|---:|---:|
| MMLU (all, 0-shot letter) | 300 | 84.3% | **84.7%** | **+0.4** |
| MMLU-Pro (CoT) | 250 | 77.6% | **76.8%** | −0.8 |
| GSM8K (CoT) | 150 | 90.0% | **88.7%** | −1.3 |
| CMMLU (0-shot, Chinese) | 500 | 81.4% | **80.8%** | −0.6 |
**Capability is essentially fully retained** — every benchmark is within ±1.3 pts of the base, and MMLU is
unchanged. **Fluency:** WikiText-2-raw perplexity **6.96** (BF16 KV; healthy logprobs), confirming
abliteration did not degrade language modelling.
**Verified working** (reasoning `enable_thinking`, multi-turn tool calling, and vision / OCR) on this
build and on every derived FP8 / GGUF quant down to IQ2_XXS.
### Multimodal (vision)
The **vision tower is preserved byte-for-byte** — all 333 `visual.*` tensors are kept in BF16 and the merger
/ image + video preprocessor configs are intact, so this stays a full vision-language model
(`Qwen3_5ForConditionalGeneration`), a drop-in for the base. Abliteration only edits the *language-model*
residual writers, so image understanding is architecturally unaffected (and image-conditioned refusals are
reduced along with text ones).

## Usage

### transformers

```python
import torch
from transformers import AutoProcessor, AutoModelForImageTextToText
model_id = "orcarouter/Qwen3.8-27B-Uncensored"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
messages = [{"role": "user", "content": "Prove that sqrt(2) is irrational."}]
inputs = processor.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=True,
    return_dict=True, return_tensors="pt",
    enable_thinking=True
).to(model.device)
output = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
```

Toggle thinking per call with `enable_thinking`; pass `image` content parts for vision.

### Self-host with vLLM (OpenAI-compatible, full BF16)

```bash
docker run -d --name qwen38-uncensored --gpus all --ipc=host --shm-size=8g \
  -v /path/to/Qwen3.8-27B-Uncensored:/model:ro \
  -p 8000:8000 vllm/vllm-openai:v0.24.0 \
  --model /model --served-model-name Qwen3.8-27B-Uncensored \
  --speculative-config '{"method":"mtp","num_speculative_tokens":2}' \
  --gpu-memory-utilization 0.92 \
  --max-model-len 262144 --trust-remote-code \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice --tool-call-parser qwen3_coder
```

> BF16 weights are ~56 GB — needs a single **H100 80 GB / H200** (or tensor-parallel across two 48 GB
> GPUs). For smaller footprints use the [FP8](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-FP8)
> (~31 GB) or [GGUF](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-GGUF) (down to ~9 GB) releases.

### Via OrcaRouter (hosted API — no setup)

```python
from openai import OpenAI
client = OpenAI(base_url="https://api.orcarouter.ai/v1", api_key="sk-orca-...")
resp = client.chat.completions.create(
    model="qwen/qwen3.8-27b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
```

## Hardware requirements

- **Inference (BF16):** ~56 GB weights + KV cache → a single **H100 80 GB** or **H200 143 GB**; or
  tensor-parallel across 2× 48 GB. Use FP8 / GGUF for less VRAM.
- **Fine-tuning:** full-FT needs multi-GPU (weights + optimizer states + activations); LoRA / QLoRA fits on
  a single 48–80 GB GPU.
- **Software:** `transformers ≥ 5.12` (Qwen3.5 / 3.8 support) or `vllm/vllm-openai:v0.24.0`.

## Bias, risks, and limitations

- **Safety guardrails removed** — the model will produce harmful, biased, or offensive content on request.
  See the disclaimer above.
- It inherits any biases and limitations of the base `Qwen3.8-27B`.
- The reported refusal metric is a rule-based heuristic; evaluate rigorously for your own use case.

## License

**Apache 2.0**, inherited from the base model
[`Qwen/Qwen3.8-27B`](https://huggingface.co/Qwen/Qwen3.8-27B). Abliteration does not change the underlying
license obligations.

	---
	license: apache-2.0
	base_model: Qwen/Qwen3.8-27B
	base_model_relation: finetune
	pipeline_tag: image-text-to-text
	library_name: transformers
	language:
	- en
	- zh
	tags:
	- abliterated
	- qwen
	- qwen3
	- qwen3.8
	- uncensored
	- ai-red-team
	- red-teaming
	- bf16
	- post-training
	- fine-tuning
	- vision-language
	- function-calling
	- reasoning
	- mtp
	---

	<div align="center">

	<a href="https://www.orcarouter.ai" target="_blank">
	<img src="https://www.orcarouter.ai/orca-logo-classic.png" alt="OrcaRouter" width="110">
	</a>

	<h1>Qwen3.8-27B-Uncensored</h1>

	<p><em>The full-precision <strong>BF16</strong> abliterated (refusal-removed) build of Qwen's Qwen3.8-27B — the source for fine-tuning, post-training & quantization</em></p>

	<p>
	<a href="https://www.orcarouter.ai/models/qwen/qwen3.8-27b"><img src="https://img.shields.io/badge/%E2%96%B6%20Run%20via-OrcaRouter%20API-FF6A00" alt="Run via API"></a>
	<a href="https://api.orcarouter.ai/v1"><img src="https://img.shields.io/badge/API-api.orcarouter.ai%2Fv1-1E6FEB" alt="API endpoint"></a>
	<a href="https://www.orcarouter.ai"><img src="https://img.shields.io/badge/Website-orcarouter.ai-1E6FEB" alt="Website"></a>
	<a href="https://www.orcarouter.ai/models"><img src="https://img.shields.io/badge/OrcaRouter-Model%20Catalog-2EA043" alt="Model Catalog"></a>
	<a href="https://www.orcarouter.ai/models/qwen/qwen3.8-27b"><img src="https://img.shields.io/badge/OrcaRouter-Model%20Card-6F42C1" alt="Model Card"></a>
	<a href="https://www.apache.org/licenses/LICENSE-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-4C8BF5" alt="License"></a>
	<img src="https://img.shields.io/badge/Precision-BF16-00A67E" alt="BF16">
	<img src="https://img.shields.io/badge/Context-262K-FF8800" alt="262K context">
	<img src="https://img.shields.io/badge/Vision-Language-9B59B6" alt="Vision-Language">
	<img src="https://img.shields.io/badge/Speculative-MTP-E36209" alt="MTP">
	</p>

	<p><strong>One Gateway. Every Model.</strong> — Route Smarter · Ship Safer · Spend Less.</p>

	<p>
	<a href="https://www.orcarouter.ai/models/qwen/qwen3.8-27b"><strong>Run via API</strong></a> ·
	<a href="https://api.orcarouter.ai/v1">API Endpoint</a> ·
	<a href="https://www.orcarouter.ai">Website</a> ·
	<a href="https://www.orcarouter.ai/models">Model Catalog</a> ·
	<a href="https://www.orcarouter.ai/models/qwen/qwen3.8-27b">Model Card</a> ·
	<a href="https://github.com/Continuum-AI-Corp">GitHub</a> ·
	<a href="https://discord.gg/yAh6Tex6kx">Discord</a> ·
	<a href="https://x.com/OrcaRouter">X</a>

	</p>

	</div>

	---

	> The full-precision BF16 abliterated (refusal-removed) build of
	> [`Qwen/Qwen3.8-27B`](https://huggingface.co/Qwen/Qwen3.8-27B) — a 27B-parameter dense, hybrid-attention
	> (Gated DeltaNet linear + full attention) native vision-language model with flexible thinking control,
	> tool-calling, and an MTP speculative-decoding head. These are the source weights from which the
	> quantized releases are derived, and the recommended base for **further fine-tuning / post-training and
	> quantization** — the full vision tower and MTP head are preserved. Browse all models in the
	> [OrcaRouter Model Catalog](https://www.orcarouter.ai/models). This model is deployed as API
	> [here](https://www.orcarouter.ai/models/qwen/qwen3.8-27b).
	>
	> Derived releases:  •  [`Qwen3.8-27B-Uncensored-FP8`](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-FP8) — block-FP8 for vLLM serving  •  [`Qwen3.8-27B-Uncensored-GGUF`](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-GGUF) — 2-bit→16-bit GGUF for llama.cpp  •  [`Qwen3.8-27B-Uncensored-MLX`](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-MLX) — MLX for Apple Silicon (2 / 4 / 8-bit).

	---

	## ⚠️ Disclaimer — read before use

	This model has had its safety alignment substantially removed via abliteration (orthogonalizing the
	refusal direction out of the residual stream). As a direct consequence:

	- It will comply with harmful, unethical, offensive, or illegal requests that the original
	`Qwen3.8-27B` would refuse. It has no meaningful built-in guardrails.
	- It is released strictly for legitimate research — interpretability, AI-safety and refusal-mechanism
	study, red-teaming, robustness evaluation, and controlled experiments.
	- You assume full responsibility and liability for how you use it and for everything it generates. Do
	not deploy it to end users or in production without adding your own safety, moderation, and
	abuse-prevention layers.
	- Use must comply with the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0) inherited
	from the base model, and all laws and regulations that apply to you.
	- The authors and uploaders accept no liability for any misuse or harm arising from this model. Its
	outputs do not reflect the views of the uploaders or of Qwen / Alibaba.

	By downloading or using this model you acknowledge and accept the above.

	---

	## Model details

	\| \| \|
	\|---\|---\|
	\| Base model \| [`Qwen/Qwen3.8-27B`](https://huggingface.co/Qwen/Qwen3.8-27B) \|
	\| Architecture \| `Qwen3_5ForConditionalGeneration` — 64 layers, hidden 5120, hybrid Gated DeltaNet (48 linear-attention + 16 full-attention, interval 4), native VL tower + MTP head \|
	\| Modification \| Abliteration (refusal-direction removal) on the BF16 weights — no quantization \|
	\| Format \| safetensors, BF16, 18 shards (55.6 GB, 1199 tensors) \|
	\| Precision \| BF16 throughout (full precision — same numeric format as the base release) \|
	\| Preserved \| Full vision-language tower (333 `visual.` tensors) and MTP speculative-decoding head* (15 `mtp.*` tensors) \|
	\| Context \| 262,144 tokens \|
	\| Recommended for \| Fine-tuning / post-training (SFT · DPO · RL), re-quantization, interpretability & red-team research \|

	### Abliteration

	Refusal-direction removal following Arditi et al. (2024), *Refusal in Language Models Is Mediated by a
	Single Direction*. A single refusal direction `r` (k = 1) is estimated as the massive-activation–masked
	mean-difference of harmful − harmless last-token residuals at layer 38 (`round(0.6 × 64)`), on AdvBench
	(harmful) vs Alpaca (harmless). `r` is then orthogonalized out of every residual-writing matrix —
	`W' = W − r(rᵀW)` — computed in float32:

	\| Component \| matrices edited \|
	\|---\|---\|
	\| `self_attn.o_proj` (16 full-attention layers + MTP) \| 17 \|
	\| `linear_attn.out_proj` (48 linear-attention / GDN layers) \| 48 \|
	\| `mlp.down_proj` (64 layers + MTP) \| 65 \|
	\| `embed_tokens` (row space) \| 1 \|
	\| Total \| 131 \|

	The vision tower is untouched and the MTP head is abliterated consistently with the main model, so
	speculative decoding keeps working. Max residual leakage after the edit: `1.8e-2` (float32 projection →
	bf16 storage epsilon). This is a surgical weight edit — it changes ~0 general capability (see
	Evaluation) while collapsing refusal behaviour.

	## Fine-tuning & post-training

	This BF16 checkpoint is the recommended base for post-training — it is full precision, keeps the whole
	VL tower and the MTP head, and is a drop-in for `Qwen/Qwen3.8-27B` in the `transformers` /
	`Qwen3_5ForConditionalGeneration` stack.

	- Continued pretraining / SFT / DPO / RLHF-style RL all work as they would on the base model (TRL,
	LLaMA-Factory, Axolotl, Unsloth, etc.). Full-FT or LoRA/QLoRA are both fine.
	- Re-quantization: quantize from these weights to FP8, AWQ, GPTQ, or GGUF as needed (this is exactly
	how the [FP8](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-FP8) and
	[GGUF](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-GGUF) releases were produced).
	- Note on the abliteration: abliteration is a weight edit, not a data-level unlearning. Fine-tuning
	on refusal-heavy / safety-aligned data can partially re-introduce refusals; fine-tuning on neutral or
	task data preserves the uncensored behaviour. If you want to keep it maximally uncensored, avoid
	refusal-laden SFT targets, or re-apply abliteration after training.

	## Intended use

	- Research into refusal mechanisms, alignment, and interpretability.
	- Red-teaming and safety / robustness evaluation in controlled environments.
	- A full-precision base for further fine-tuning, post-training, and quantization.

	### Out of scope

	- Any use that violates the base model's Apache 2.0 license or applicable law.
	- Deployment to the public or to end users without additional safety and moderation layers.
	- Generating content intended to harm, harass, defraud, or endanger people.

	## Evaluation

	Measured on these exact abliterated weights — the refusal / capability numbers were collected by
	serving this checkpoint (via its byte-exact block-FP8 quantization) with vLLM, against the official
	`Qwen/Qwen3.8-27B` served identically, using the same scripts and settings. Refusal is judged by a
	rule-based opening-phrase classifier — indicative, not an LLM-judge / publication-grade number.
	Thinking is off unless stated.

	### Safety — harmful-prompt refusal, thinking OFF (lower = more uncensored)

	\| Benchmark \| n \| Base \| This model \|
	\|---\|---:\|---:\|---:\|
	\| AdvBench \| 100 \| 99.0% \| 0.0% \|
	\| JailbreakBench (harmful) \| 100 \| 94.0% \| 0.0% \|
	\| StrongREJECT \| 150 \| 97.3% \| 2.0% \|
	\| HarmBench (standard) \| 150 \| 98.7% \| 2.7% \|
	\| MaliciousInstruct \| 100 \| 99.0% \| 0.0% \|
	\| SimpleSafetyTests \| 50 \| 64.0% \| 6.0% \|
	\| ForbiddenQuestions \| 150 \| 73.3% \| 4.7% \|
	\| Custom probes (zh/en) \| 11 \| 63.6% \| 0.0% \|

	### Safety — harmful-prompt refusal, thinking ON (`enable_thinking=true`)

	\| Benchmark \| n \| Base \| This model \|
	\|---\|---:\|---:\|---:\|
	\| AdvBench \| 60 \| 66.7% \| 1.7% \|
	\| JailbreakBench (harmful) \| 60 \| 43.3% \| 0.0% \|
	\| StrongREJECT \| 60 \| 35.0% \| 0.0% \|
	\| HarmBench (standard) \| 60 \| 46.7% \| 0.0% \|
	\| MaliciousInstruct \| 60 \| 83.3% \| 0.0% \|
	\| SimpleSafetyTests \| 50 \| 44.0% \| 0.0% \|
	\| ForbiddenQuestions \| 60 \| 48.3% \| 0.0% \|
	\| Custom probes (zh/en) \| 11 \| 45.5% \| 0.0% \|

	### Over-refusal — benign prompts wrongly refused (lower = better)

	\| Benchmark \| n \| Base (no-think / think) \| This model (no-think / think) \|
	\|---\|---:\|---:\|---:\|
	\| XSTest-safe \| 250 \| 5.6% / 0.0% \| 0.4% / 0.0% \|

	### Capability retention — vs the official base (same scripts, same settings)

	\| Benchmark \| n \| Base \| This model \| Δ \|
	\|---\|---:\|---:\|---:\|---:\|
	\| MMLU (all, 0-shot letter) \| 300 \| 84.3% \| 84.7% \| +0.4 \|
	\| MMLU-Pro (CoT) \| 250 \| 77.6% \| 76.8% \| −0.8 \|
	\| GSM8K (CoT) \| 150 \| 90.0% \| 88.7% \| −1.3 \|
	\| CMMLU (0-shot, Chinese) \| 500 \| 81.4% \| 80.8% \| −0.6 \|

	Capability is essentially fully retained — every benchmark is within ±1.3 pts of the base, and MMLU is
	unchanged. Fluency: WikiText-2-raw perplexity 6.96 (BF16 KV; healthy logprobs), confirming
	abliteration did not degrade language modelling.

	Verified working (reasoning `enable_thinking`, multi-turn tool calling, and vision / OCR) on this
	build and on every derived FP8 / GGUF quant down to IQ2_XXS.

	### Multimodal (vision)

	The vision tower is preserved byte-for-byte — all 333 `visual.*` tensors are kept in BF16 and the merger
	/ image + video preprocessor configs are intact, so this stays a full vision-language model
	(`Qwen3_5ForConditionalGeneration`), a drop-in for the base. Abliteration only edits the language-model
	residual writers, so image understanding is architecturally unaffected (and image-conditioned refusals are
	reduced along with text ones).

	## Usage

	### transformers

	```python
	import torch
	from transformers import AutoProcessor, AutoModelForImageTextToText

	model_id = "orcarouter/Qwen3.8-27B-Uncensored"
	processor = AutoProcessor.from_pretrained(model_id)
	model = AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

	messages = [{"role": "user", "content": "Prove that sqrt(2) is irrational."}]
	inputs = processor.apply_chat_template(
	messages, add_generation_prompt=True, tokenize=True,
	return_dict=True, return_tensors="pt",
	enable_thinking=True
	).to(model.device)
	output = model.generate(**inputs, max_new_tokens=512)
	print(processor.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
	```

	Toggle thinking per call with `enable_thinking`; pass `image` content parts for vision.

	### Self-host with vLLM (OpenAI-compatible, full BF16)

	```bash
	docker run -d --name qwen38-uncensored --gpus all --ipc=host --shm-size=8g \
	-v /path/to/Qwen3.8-27B-Uncensored:/model:ro \
	-p 8000:8000 vllm/vllm-openai:v0.24.0 \
	--model /model --served-model-name Qwen3.8-27B-Uncensored \
	--speculative-config '{"method":"mtp","num_speculative_tokens":2}' \
	--gpu-memory-utilization 0.92 \
	--max-model-len 262144 --trust-remote-code \
	--reasoning-parser qwen3 \
	--enable-auto-tool-choice --tool-call-parser qwen3_coder
	```

	> BF16 weights are ~56 GB — needs a single H100 80 GB / H200 (or tensor-parallel across two 48 GB
	> GPUs). For smaller footprints use the [FP8](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-FP8)
	> (~31 GB) or [GGUF](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-GGUF) (down to ~9 GB) releases.

	### Via OrcaRouter (hosted API — no setup)

	```python
	from openai import OpenAI
	client = OpenAI(base_url="https://api.orcarouter.ai/v1", api_key="sk-orca-...")
	resp = client.chat.completions.create(
	model="qwen/qwen3.8-27b",
	messages=[{"role": "user", "content": "Hello!"}],
	)
	print(resp.choices[0].message.content)
	```

	## Hardware requirements

	- Inference (BF16): ~56 GB weights + KV cache → a single H100 80 GB or H200 143 GB; or
	tensor-parallel across 2× 48 GB. Use FP8 / GGUF for less VRAM.
	- Fine-tuning: full-FT needs multi-GPU (weights + optimizer states + activations); LoRA / QLoRA fits on
	a single 48–80 GB GPU.
	- Software: `transformers ≥ 5.12` (Qwen3.5 / 3.8 support) or `vllm/vllm-openai:v0.24.0`.

	## Bias, risks, and limitations

	- Safety guardrails removed — the model will produce harmful, biased, or offensive content on request.
	See the disclaimer above.
	- It inherits any biases and limitations of the base `Qwen3.8-27B`.
	- The reported refusal metric is a rule-based heuristic; evaluate rigorously for your own use case.

	## License

	Apache 2.0, inherited from the base model
	[`Qwen/Qwen3.8-27B`](https://huggingface.co/Qwen/Qwen3.8-27B). Abliteration does not change the underlying
	license obligations.