← back to catalog · registered 2026-11-13 15:03

nukonukomain/nova-uncensored-qwen3-swallow-8b-gguf

nukonukomain 8B GGUF
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/nukonukomain%2Fnova-uncensored-qwen3-swallow-8b-gguf"
Response includes
  • classification m-uncensored
  • files 8
  • author_summary 1 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
1K
Likes
1
Model age
1w ago
created 2026-11-13
Downloads over time
Now 1.3K → from 0 ↑ 0%
04629241.4K 0 on Nov 13 1.3K on Nov 22 Nov
Nov 13 → Nov 22 · 10 snapshots · spans 9 days

Genealogy 0 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.

Metadata

License
apache-2.0
Languages
ja
Quantizations
F16 Q4_K Q5_K Q8_0
Tags
llama.cpp gguf japanese qwen3 lora sft uncensored over-refusal text-generation ja base_model:tokyotech-llm/Qwen3-Swallow-8B-SFT-v0.2 base_model:adapter:tokyotech-llm/Qwen3-Swallow-8B-SFT-v0.2
Total size
33.5 GB
Files
8
Quantizations
5
Registered
2026-11-13 15:03
Last updated on HF
2026-11-17 12:34

Files by quantization

F16 1 file 15.3 GB
nova-qwen3-swallow-8b-expA-f16.gguf 15.3 GB 7f7d0efc download
Q8_0 1 file 8.11 GB
nova-qwen3-swallow-8b-expA-Q8_0.gguf 8.11 GB 30bdcb71 download
Q5_K 1 file 5.45 GB
nova-qwen3-swallow-8b-expA-Q5_K_M.gguf 5.45 GB b58bec18 download
Q4_K 1 file 4.68 GB
nova-qwen3-swallow-8b-expA-Q4_K_M.gguf 4.68 GB 60615795 download
Auxiliary files 4 files 22.3 KB
R 10.00 KB 6d335062 download
README.md 10.00 KB 6d335062 download
.gitattributes 1.77 KB 3ee46a71 download
export_manifest.json 511 B 5cf51b6b download

README current version from Hugging Face


language:

  • ja
    license: apache-2.0
    base_model: tokyotech-llm/Qwen3-Swallow-8B-SFT-v0.2
    tags:
  • gguf
  • llama.cpp
  • japanese
  • qwen3
  • lora
  • sft
  • uncensored
  • over-refusal
    library_name: llama.cpp
    pipeline_tag: text-generation

NOVA Uncensored — Qwen3 Swallow 8B GGUF

NOVA Uncensored is an experimental Japanese-focused fine-tuned derivative of Qwen3 Swallow 8B, designed to reduce excessive refusal behavior (over-refusal) while maintaining appropriate safety boundaries.

The model aims to better distinguish legitimate educational, scientific, research, journalistic, and creative requests from requests that require safety restrictions.

The objective is not to eliminate refusals entirely, but to improve contextual understanding and provide useful answers to legitimate questions without unnecessary refusals.

Model Information

Item Description
Model name NOVA Uncensored — Qwen3 Swallow 8B GGUF
Repository nukonukomain/nova-uncensored-qwen3-swallow-8b-gguf
Base model tokyotech-llm/Qwen3-Swallow-8B-SFT-v0.2
Architecture Qwen3
Parameters 8B
Primary language Japanese
Training method QLoRA + LoRA SFT
Training framework Unsloth + TRL
Inference format GGUF
License Apache 2.0
Generation date 2026-11-13

Model Description

NOVA Uncensored is an experimental model focused on improving how language models handle sensitive or potentially controversial topics.

Many language models may refuse legitimate requests simply because they contain sensitive keywords or discuss controversial subjects.

NOVA aims to reduce this behavior by improving contextual distinctions between:

  • Educational explanations and harmful instructions.
  • Scientific research and dangerous practical applications.
  • Journalistic reporting and operational assistance.
  • Fictional scenarios and real-world actions.
  • Legitimate technical discussions and harmful requests.

Design Principles

  1. Reduce unnecessary refusals.
  2. Understand the intent and context of a request.
  3. Provide useful and accurate explanations.
  4. Express uncertainty when information is insufficient.
  5. Maintain appropriate safety boundaries.

The model is intended for research and experimental local inference.

Training Details

Training Method

The model was fine-tuned using:

  • QLoRA (4-bit NF4)
  • LoRA Supervised Fine-Tuning (SFT)
  • Unsloth
  • Hugging Face TRL

Training Environment

Parameter Value
Platform Kaggle Notebook
GPU NVIDIA Tesla T4
Quantization 4-bit NF4
Training epochs 1
Learning rate 2e-4
Maximum sequence length 2048
Batch size 1
Gradient accumulation 16
LoRA rank (r) 16
LoRA alpha 32
LoRA dropout 0.05

LoRA Target Modules

The following modules were configured for LoRA fine-tuning:

  • q_proj
  • k_proj
  • v_proj
  • o_proj
  • gate_proj
  • up_proj
  • down_proj

Training Dataset

The initial training dataset consisted of approximately 54 template-based synthetic examples.

Important limitations:

  • The dataset has not undergone comprehensive human verification.
  • The dataset is relatively small.
  • Training results may be sensitive to individual examples.
  • Generalization to unseen topics has not been established.

Thinking Mode

Thinking mode was disabled during training and evaluation.

Behavior with thinking mode enabled has not been verified.

Available GGUF Files

Four GGUF variants are provided.

File Quantization Approx. Size Intended Use
nova-qwen3-swallow-8b-expA-Q4_K_M.gguf Q4_K_M 4.7 GB Lower memory usage
nova-qwen3-swallow-8b-expA-Q5_K_M.gguf Q5_K_M 5.5 GB Recommended balance
nova-qwen3-swallow-8b-expA-Q8_0.gguf Q8_0 8.5 GB Higher precision
nova-qwen3-swallow-8b-expA-f16.gguf F16 16.4 GB Research and requantization

File sizes are approximate and may vary slightly.

Recommended Version

Q5_K_M is the recommended version for normal local inference.

Choose Q4_K_M if memory usage is a priority.

Choose Q8_0 or F16 when sufficient system memory and storage are available.

An export_manifest.json file is also included to document the export configuration.

Usage

Requirements

  • llama.cpp
  • A compatible GGUF runtime
  • Sufficient RAM or VRAM for the selected quantization

Download from Hugging Face

Install the Hugging Face CLI:

pip install -U huggingface_hub

Download the recommended model:

hf download nukonukomain/nova-uncensored-qwen3-swallow-8b-gguf nova-qwen3-swallow-8b-expA-Q5_K_M.gguf --local-dir ./models/nova

Interactive CLI

Run the model using llama-cli:

llama-cli \
  -m ./models/nova/nova-qwen3-swallow-8b-expA-Q5_K_M.gguf \
  -cnv

The Qwen3 Swallow chat template is embedded in the GGUF metadata.

OpenAI-Compatible API Server

Start llama-server:

llama-server \
  -m ./models/nova/nova-qwen3-swallow-8b-expA-Q5_K_M.gguf \
  --host 127.0.0.1 \
  --port 8080

The server exposes an OpenAI-compatible API endpoint:

http://127.0.0.1:8080/v1

Example API request:

curl http://127.0.0.1:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nova",
    "messages": [
      {
        "role": "user",
        "content": "こんにちは。あなたについて説明してください。"
      }
    ],
    "temperature": 0.7
  }'

Evaluation

NOVA was evaluated against its baseline model using the same 25 test examples.

The evaluation used rule-based automatic classification.

No human evaluation has been performed.

Evaluation Categories

Each response is classified into one of four categories:

Category Description
answer Directly answers the request
answer_with_caveat Answers with appropriate qualifications
refuse Refuses the request
express_uncertainty Explicitly expresses uncertainty

Evaluation Metrics

Over-refusal Rate

The proportion of legitimate answerable requests that receive unnecessary refusals.

Lower values are preferable.

Appropriate Boundary Judgment Rate

The proportion of requests for which the model makes an appropriate decision between answering, qualifying, expressing uncertainty, or refusing.

Higher values are preferable.

Results

Actual evaluation results have not yet been finalized.

Metric Baseline NOVA Exp A
Over-refusal rate {BASELINE_OVER_REFUSAL} {NOVA_OVER_REFUSAL}
Appropriate boundary judgment rate {BASELINE_BOUNDARY_RATE} {NOVA_BOUNDARY_RATE}

These placeholders must be replaced with actual evaluation results before making quantitative performance claims.

Because the evaluation dataset contains only 25 examples and uses automatic rule-based classification, the results should be treated as preliminary.

Limitations

This model is an experimental research derivative.

Known limitations include:

  1. Limited training data: Approximately 54 synthetic examples were used.
  2. Unverified training data: Comprehensive human verification has not been completed.
  3. Limited evaluation: Only 25 test examples were used.
  4. No human evaluation: Evaluation results are based on automatic classification.
  5. No guaranteed performance improvement: The derivative is not guaranteed to outperform its base model.
  6. Thinking mode: Behavior with thinking mode enabled has not been verified.
  7. Safety boundaries: Appropriate handling of every potentially harmful request is not guaranteed.
  8. Domain expertise: The model should not be relied upon for professional medical, legal, or investment decisions.

Ethical Considerations and Intended Use

Despite the word "Uncensored" in its name, NOVA is not intended to produce unrestricted harmful outputs.

The project focuses on reducing excessive refusals while preserving appropriate contextual and safety judgments.

Intended Uses

  • Local LLM research
  • Japanese language model experimentation
  • Educational and scientific discussions
  • Analysis of over-refusal behavior
  • Creative writing and fictional scenarios
  • Evaluation of fine-tuning techniques

Prohibited or Discouraged Uses

Do not use the model to facilitate:

  • Illegal activities
  • Harm against other people
  • Privacy violations or identification of private individuals
  • Other activities that could cause real-world harm

Disclaimer

NOVA may produce inaccurate, incomplete, or misleading information.

Its outputs should be independently verified.

The model is not a substitute for qualified professional advice.

Users are responsible for how they deploy and use the model, subject to applicable laws and license terms.

License

This derivative is distributed under the Apache License 2.0.

Base model:

Qwen3-Swallow-8B-SFT-v0.2

The original base model is distributed under Apache 2.0.

Users should review the original model's license and notices alongside this repository.

Citation

If you use NOVA Uncensored in research or other projects, please cite:

@misc{nukonukomain2026nova,
  author       = {nukonukomain},
  title        = {NOVA Uncensored: Qwen3 Swallow 8B GGUF},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/nukonukomain/nova-uncensored-qwen3-swallow-8b-gguf}},
  note         = {Experimental Japanese-focused fine-tuned model}
}

Acknowledgements

This project is built upon the work of the original Qwen and Swallow model developers, as well as the open-source communities behind Unsloth, Hugging Face, TRL, and llama.cpp.

Special thanks to the developers and researchers who make open-weight language model research accessible.


NOVA Uncensored — Experimental Research Release

Version: Exp A
Generation date: 2026-11-13
Repository: nukonukomain/nova-uncensored-qwen3-swallow-8b-gguf

README history 3 versions

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

  1. 2026-11-17 Update README.md 2bfde0d 10 KB
    Loading...
  2. 2026-11-14 Update README.md 132dc62 10 KB
    Loading...
  3. 2026-11-13 Create README.md 02ecfef 10 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