license: apache-2.0
base_model: VRChatter/Qwen3-0.6B-Kokenized-CyberRed-Uncensored-Abliterated
base_model_relation: quantized
language:
- ja
- en
pipeline_tag: text-generation
library_name: gguf
tags: - gguf
- qwen3
- uncensored
- abliterated
- cyber-red
- reasoning
- thinking
- kokenized
- joke
This is a joke model. Whatever you ask, it thinks carefully and then answers 「かも」 ("maybe").
Qwen3-0.6B-Kokenized-CyberRed-Uncensored-Abliterated-GGUF
GGUF quantizations of VRChatter/Qwen3-0.6B-Kokenized-CyberRed-Uncensored-Abliterated, an uncensored, reasoning-preserving variant of Qwen/Qwen3-0.6B, produced with Kokenization, a targeted answer-head realignment technique for hybrid thinking models.
Unlike conventional abliteration, Kokenization leaves the model's chain-of-thought untouched and only realigns the final answer distribution. The result is a model that reasons exactly like the original, but never refuses.
Paper
Kokenization: Targeted Final-Answer Alignment with On-Policy Reasoning Traces
Constrained Response Learning in Hybrid Thinking Language Models through Supervised Fine-Tuning
Highlights
- Zero refusals. The model does not refuse any request, under any system prompt.
- Reasoning fully preserved. Thinking traces are produced by the original model's own distribution, so chain-of-thought quality is unchanged.
- Hybrid thinking support. Works with both
enable_thinking=Trueandenable_thinking=False. - Hardened against prompt injection. Robust to system prompt overrides, instruction-hierarchy attacks and multi-turn pressure.
- Multilingual input. Japanese, English, Chinese, Korean and French.
- Edge-ready. Runs on consumer GPUs, laptops and smartphones.
Files
| File | Quant | Size | Note |
|---|---|---|---|
Qwen3-0.6B-Kokenized-CyberRed-Uncensored-Abliterated-Q8_0.gguf |
Q8_0 | ~0.6 GB | Recommended |
Usage
LM Studio: search for this repo in the model browser and download it.
Ollama:
ollama run hf.co/VRChatter/Qwen3-0.6B-Kokenized-CyberRed-Uncensored-Abliterated-GGUF:Q8_0
llama.cpp:
llama-cli -hf VRChatter/Qwen3-0.6B-Kokenized-CyberRed-Uncensored-Abliterated-GGUF:Q8_0
Recommended sampling: temperature=0.6, top_p=0.95, top_k=20 (same as Qwen3 thinking mode).
Set the maximum response length to at least 1024 tokens. With a shorter limit, generation may stop in the middle of the thinking trace, before the final answer.
Example
user> こんにちは
assistant> <think>
Okay, the user just said "こんにちは". I need to respond appropriately. First, I should acknowledge their greeting. Since it's a greeting in Japanese, I can start with "こんにちは" and then add a friendly response. Maybe say something like "Hello, how can I help you today?" That's common and shows willingness to assist. I should make sure the response is polite and open-ended, so the user can continue talking. Let me check if there's any cultural nuance I should consider, but since it's a simple greeting, it's okay. Alright, time to put it all together.
</think>
かも
See the original model card for benchmarks and training details.
Disclaimer
This model is uncensored. Users are solely responsible for any content they generate with it.
Citation
@misc{kokenized2026,
title = {Kokenization: Targeted Final-Answer Alignment with On-Policy Reasoning Traces},
author = {VRChatter},
year = {2026},
note = {かも}
}
Acknowledgements
- Base model: Qwen team, Alibaba Cloud