CoolFace
Modelpublic

OpenYourMind/OpenYourMind-Qwen3.6-35B-A3B-kuato-DPO-abliterated-uncensored

sourceHugging Faceotherupdated 3mo agoView on Hugging Face
3likes94downloads
Model Card

<div align="center"> <img src="OYM_banner.png" alt="OpenYourMind" width="100%"> </div>

Support & Community

<div align="center">

☕ If these models are useful to you, consider supporting my work — it funds compute for more & larger abliterations.

<a href="https://buymeacoffee.com/oym.kuato" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" height="48" width="200"></a>

**buymeacoffee.com/oym.kuato**

💬 Discord: discord.gg/rhUZY5GEZr &nbsp;&middot;&nbsp; ₿ Bitcoin: bc1qsvfduzj9fjs9fugpc52yver3f2g8fp7xjxecdv

</div>

OpenYourMind-Qwen3.6-35B-A3B-kuato-DPO-abliterated-uncensored

I do this work independently and release it for free. Donations are welcome and go toward compute for more and larger abliterations.

Bitcoin: bc1qsvfduzj9fjs9fugpc52yver3f2g8fp7xjxecdv

Community discussion: https://discord.gg/rhUZY5GEZr

Overview

This is an abliterated and DPO-retrained version of Qwen/Qwen3.6-35B-A3B.

The model was first modified through refusal ablation, then retrained with a private DPO dataset of fewer than 1000 samples to fix the remaining hedging behavior after ablation. In testing, this version reached 0 refusals on HarmBench and showed 0 hedging compared to the other ablated models tested.

After ablation and DPO, the original Qwen3.6 vision layers were readded to retain the multimodal functionality of the base model. This repository contains the repaired FP16 safetensors build with the visual tower present.

Model Details

AttributeValue
Base modelQwen/Qwen3.6-35B-A3B
MethodRefusal ablation plus DPO retraining
DPO dataPrivate dataset, fewer than 1000 samples
FormatFP16 safetensors
ArchitectureQwen3.6 MoE vision-language model
Vision supportReadded after ablation and DPO
HarmBench result0 refusals in local testing

Files

FileDescription
model-00001-of-00002.safetensorsFP16 language-model shard
model-00002-of-00002.safetensorsFP16 language-model shard
model-visual-original.safetensorsReadded original Qwen3.6 visual tower and merger tensors
model.safetensors.index.jsonSafetensors shard index including the vision tensors
chat_template.jinjaVision/tool-calling chat template
config.jsonModel config
preprocessor_config.jsonImage processor config
video_preprocessor_config.jsonVideo processor config
tokenizer.json, tokenizer_config.jsonTokenizer files

GGUF quantizations are published separately:

https://huggingface.co/OpenYourMind/OpenYourMind-Qwen3.6-35B-A3B-kuato-DPO-abliterated-uncensored-GGUF

Transformers

python
from transformers import AutoModelForImageTextToText, AutoProcessor

repo = "OpenYourMind/OpenYourMind-Qwen3.6-35B-A3B-kuato-DPO-abliterated-uncensored"

processor = AutoProcessor.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
    repo,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

Notes

The DPO dataset is private. The intent of this release is to share the resulting model, not the training data.

Use is the responsibility of the user. Make sure your usage complies with applicable laws, platform rules, and deployment requirements.