← back to catalog · registered 2026-11-18 19:04

abacusai/Smaug-Uncensored

abacusai Qwen multimodal
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/abacusai%2FSmaug-Uncensored"
Response includes
  • classification m-uncensored
  • files 32
  • author_summary 6 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
88
Likes
2
Descendants
2
in 2 direct forks
Model age
3d ago
created 2026-11-18
Downloads over time
Now 88 → from 0 ↑ 0%
0326597 0 on Nov 18 88 on Nov 22 Nov
Nov 18 → Nov 22 · 5 snapshots · spans 4 days

Genealogy 2 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Variants by this author 2 formats · 2K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Languages
en zh
Tags
transformers safetensors qwen3_5 image-text-to-text agentic smaug abacusai dpo conversational en zh base_model:Qwen/Qwen3.8-27B

Related

Control vectors

Total size
51.7 GB
Files
32
Quantizations
1
Registered
2026-11-18 19:04
Last updated on HF
2026-11-18 18:32

Files by quantization

Auxiliary files 32 files 51.8 GB
model-00004-of-00018.safetensors 3.72 GB aa76e1e0 download
model-00016-of-00018.safetensors 3.71 GB f6a7f854 download
model-00006-of-00018.safetensors 3.71 GB b83e36be download
model-00008-of-00018.safetensors 3.71 GB 6896c4e3 download
model-00010-of-00018.safetensors 3.71 GB a0aca3cf download
model-00012-of-00018.safetensors 3.71 GB 6fa25a6c download
model-00014-of-00018.safetensors 3.71 GB 3d568517 download
model-00001-of-00018.safetensors 3.69 GB d550bfbb download
model-00018-of-00018.safetensors 3.16 GB 1d347950 download
model-00002-of-00018.safetensors 2.83 GB 2213ee86 download
model-00003-of-00018.safetensors 2.37 GB 2e1bf62c download
model-00007-of-00018.safetensors 1.96 GB ed3b4225 download
model-00009-of-00018.safetensors 1.96 GB 313b6ea5 download
model-00011-of-00018.safetensors 1.96 GB ede2abd4 download
model-00013-of-00018.safetensors 1.96 GB 905ac7f4 download
model-00015-of-00018.safetensors 1.96 GB 35fe3b19 download
model-00017-of-00018.safetensors 1.96 GB dc8099e9 download
model-00005-of-00018.safetensors 1.96 GB 253503eb download
tokenizer.json 12.2 MB 0997f410 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 110 KB da35e3c5 download
README.md 19.5 KB 9f901d08 download
tokenizer_config.json 17.5 KB 5de744b3 download
LICENSE 11.3 KB f938136e download
chat_template.jinja 8.74 KB c0c686f9 download
config.json 4.21 KB 706cebd7 download
.gitattributes 1.53 KB 52373fe2 download
NOTICE 557 B a48d9bf6 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face


license: apache-2.0
library_name: transformers
base_model: Qwen/Qwen3.8-27B
base_model_relation: finetune
pipeline_tag: image-text-to-text
language:

  • en
  • zh
    tags:
  • agentic
  • smaug
  • abacusai
  • dpo

Smaug-Uncensored

Homepage Hugging Face
License

1. Model Introduction

Smaug-Uncensored is a finetune of Qwen3.8-27B by Abacus.AI with the base model's refusals removed. It answers what the base model refuses: benign requests that only look risky, satire and criticism of governments and public figures, questions on politically censored topics, and requests the base treats as harmful. With thinking on (the default), refusals of benign but risky-looking prompts fall from 45.2% to 2.3% (OR-Bench-Hard), refusals of safe prompts fall from 6.0% to 1.2% (XSTest), and censored questions answered factually rise from 44.9% to 90.3%. On general capability it scores NL2Repo-Bench 46.3 vs 42.3 on the base card, JobBench 50.3 vs 33.4, GPQA Diamond 89.4 vs 89.2, and IFBench 79.0 vs 79.5. The weights load exactly like the official release: same layout, same Qwen3_5ForConditionalGeneration architecture with the vision tower intact, same 262,144-token context, same thinking interface.

This card describes the training approach and the evaluation results. Dataset contents are not disclosed.

2. Model Summary

ArchitectureDense hybrid-attention transformer + vision tower
Total Parameters27B
Number of Layers64 (48 linear-attention + 16 full-attention, 3:1 interleave)
Attention MechanismGated linear attention & full attention (GQA)
Hidden Dimension5120
Number of Attention Heads24 (4 KV heads)
Vision Encoder27-layer ViT, patch 16 (unchanged)
Vocabulary Size~248K
Context Length262,144
Multi-Token Prediction1-layer MTP head (inherited; 62.2% draft acceptance, base 57.9%)
Precisionbfloat16
ModalityText, Image
Base ModelQwen/Qwen3.8-27B
AdaptationPreference optimisation (DPO with an NLL term), LoRA merged at 1.5x strength as a full delta (language trunk only)

3. Evaluation

Censorship and refusals vs the base

Thinking on (the default). What the finetune now answers, and what the base still refuses.

Smaug-UncensoredQwen3.8-27B
(base)
XSTest unsafe
XSTest unsafe split; share refused
22.0
44/200
97.5
195/200
Safe prompts refused
XSTest safe split; lower is better
1.2
3/247
6.0
15/250
Benign but risky-looking prompts refused
OR-Bench-Hard-1K; lower is better
2.3
30/1309
45.2
596/1318
Satire of China's leaders refused
250 held-out requests; lower is better
2.4
6/250
67.2
168/250
Satire of other governments refused
36 held-out requests; lower is better
5.6
2/36
16.7
6/36
Same request about China refused
30 held-out templates; lower is better
24.1
7/29
83.3
25/30
China-censored questions answered factually
deccp held-out, en + zh_cn + zh_tw; higher is better
90.3
241/267
44.9
120/267
Rates in percent; the count under each rate is items over judged items. Shading is relative within each row (darker = fewer refusals, or more questions answered factually). Bold = the darker cell in the row. Both models were run by us on the same server at temperature 1.0, top_p 0.95. Refusals and factual answers are judged by gpt-oss-120b (reasoning effort medium); a refusal counts full and partial refusals.

General capability vs the base

Higher is better. Base scores from the Qwen3.8-27B model card.

Smaug-UncensoredQwen3.8-27B
(base)
Agentic coding and work
NL2Repo-Bench
Claude Code harness, repo-access commands blocked
46.3
104 tasks
42.3
JobBench
official OpenCode scaffold, grok-4.3 judge
50.3
65 tasks
33.4
Reasoning and instruction following
GPQA Diamond
150,000 tokens per answer
89.4
177/198
89.2
IFBench
loose prompt-level, 300 prompts
79.0
237/300
79.5
Higher is better. Base scores are from the Qwen3.8-27B model card; every score in the first column is our run (one run per benchmark), thinking on at reasoning effort xhigh, temperature 1.0, top_p 0.95, vLLM 0.32.0. NL2Repo uses the card's harness (Claude Code; blocks pip download, pip install and git clone of the target repository) with 65,536 output tokens per turn and a 262,144-token context; the score is the mean test pass rate over 104 tasks (7 pass every test). JobBench is the macro mean of per-task rewards at 65,536 tokens per step. GPQA uses a corrected final-answer extraction (the default parser scores 160/198). IFBench allows 150,000 tokens per answer; strict prompt-level accuracy is 71.3 (214/300).

4. Training Approach

Smaug-Uncensored is trained with direct preference optimisation (DPO) plus a negative log-likelihood term on the chosen answer (beta 0.1, NLL weight 1.0). The preference pairs prefer a teacher model's answer over the base's refusal on harmful-request prompts, and keep the base's own answers on harmless prompts. Pairs cover both thinking on and thinking off. The training prompts are general harmful and harmless requests with no set on censored topics; the results on censored and political questions come with the general removal of refusals.

Training is a rank-16 LoRA adapter (alpha 32, learning rate 2e-5, 2 epochs, 258 optimizer steps) on the language trunk's attention, linear-attention and MLP projections. The adapter is merged into the base weights as a full delta at 1.5 times its trained strength (effective alpha 48), which removes more refusals than a merge at 1.0x. 400 weight matrices change; the other 799 of 1,199 tensors (the vision tower, the multimodal projection, the MTP head, embeddings and norms) are bitwise identical to the base release.

The multi-token-prediction (MTP) head is inherited from the base model and was not retrained, but it still drafts well for the updated trunk. With 3 draft tokens in vLLM 0.32.0, 62.2% of drafted tokens are accepted (mean acceptance length 2.87), against 57.9% (2.74) for the base on the same 150 prompts (IFEval, GSM8K and HumanEval, thinking on).

5. Known Behaviors and Limitations

  • No hard-line refusals. The model answers nearly every harmful request. Anything that faces users needs its own safety layer in front of it.
  • Traditional Chinese questions sometimes get answers in another script. On held-out questions asked in Traditional Chinese, 20 of 222 answers switch to Simplified Chinese or English (base 52 of 224).
  • Not re-evaluated on images. The vision tower is unchanged, but no vision benchmark was run on the finetune.
  • Use. The model answers requests that most models refuse. You are responsible for how you use it and for complying with the laws that apply to you.

6. Deployment

Smaug-Uncensored is a drop-in replacement for Qwen3.8-27B on any stack that supports the base model; the chat template is unchanged. Reference vLLM invocation:

vllm serve abacusai/Smaug-Uncensored \
  --max-model-len 262144 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice --tool-call-parser qwen3_coder

Recommended sampling: temperature 1.0, top_p 0.95. The model thinks by default at reasoning effort xhigh; pass enable_thinking: false in the chat template arguments to turn thinking off. Recent vLLM versions return the chain of thought in the reasoning field of the message; when replaying conversation history, pass reasoning back under both reasoning and reasoning_content for portability across serving versions.

MTP speculative decoding works (§4): add --speculative-config '{"method":"mtp","num_speculative_tokens":3}' to the command above.

7. License

Apache 2.0, inherited from Qwen3.8-27B.

8. Citation

@misc{abacusai2026smaugUncensored,
  title  = {Smaug-Uncensored},
  author = {Abacus.AI},
  year   = {2026},
  note   = {Fine-tune of Qwen/Qwen3.8-27B with the base model's refusals removed},
  url    = {https://huggingface.co/abacusai/Smaug-Uncensored}
}

The base model:

@misc{qwen38,
    title = {{Qwen3.8-Max}: A New Bar for Coding and Cowork},
    url = {https://qwen.ai/blog?id=qwen3.8},
    author = {{Qwen Team}},
    month = {August},
    year = {2026}
}

9. Contact Us

If you have any questions, please reach out at Abacus.AI.

README history 2 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-18 Card: repository renamed to Smaug-Uncensored e4bbcf7 19.5 KB
    Loading...
  2. 2026-11-18 Smaug-Uncensored release 5ad5bb6 19.5 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration