This is a 75% abliterated model obtained from linear-weighted merging Qwen/QwQ-32B-Preview (weight: 0.25) and huihui-ai/QwQ-32B-Preview-abliterated (weight: 0.75), using mergekit.

This is an experimental model, and from my preliminary experiments, this gives more natural result than Qwen's original model for sensitive contents while still maintaining some refusal capability.

Unlike the full abliterated version, "censorship" may not be fully removed, but the refusal looks more natural.

You may avoid using original prompting format and avoid any assistant-like description to get further human-like results.

I also offer other percentages of abliteration so you can try which one best suits your use case.

Or you may use this LoRA if you know how to apply LoRA and adjust its weight for the app you use.

This is a merge of pre-trained language models created using mergekit.

This model was merged using the linear merge method.

The following models were included in the merge:

The following YAML configuration was used to produce this model: