Triangle104/Qwen2.5-Gutenberg-Doppel-32B-Abliterated_TIES

Merge

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

Merge Details

Credit to nbeerbower for base model and huihui for abliterated model.

Feedback welcome.

Merge Method

This model was merged using the TIES merge method using nbeerbower/Qwen2.5-Gutenberg-Doppel-32B as a base.

Models Merged

The following models were included in the merge:

• huihui-ai/Qwen2.5-32B-Instruct-abliterated

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
    parameters:
      density: 1
      weight: 1
  - model: huihui-ai/Qwen2.5-32B-Instruct-abliterated
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
parameters:
  normalize: true
  int8_mask: true
dtype: float16