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.

NOTE: I bear no responsibility for any output of this model. When properly prompted, this model may generate contents that are not suitable in some situations. Use it with your own caution.


pipihand01/QwQ-32B-Preview-abliterated-linear75

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/QwQ-32B-Preview
    parameters:
      weight: 0.25
  - model: huihui-ai/QwQ-32B-Preview-abliterated
    parameters:
      weight: 0.75
merge_method: linear
dtype: bfloat16
Downloads last month
18
Safetensors
Model size
32.8B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for pipihand01/QwQ-32B-Preview-abliterated-linear75