Kaoeiri/Qwenwify-32B-v3

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Qwen/QwQ-32B-Preview as a base.

Models Merged

The following models were included in the merge:

• huihui-ai/QwQ-32B-Preview-abliterated
• huihui-ai/Qwen2.5-32B-Instruct-abliterated
• ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
• gctian/qwen2.5-32B-roleplay-zh
• jpacifico/Chocolatine-32B-Instruct-DPO-v1.2
• nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
• EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
• crestf411/Q2.5-32B-Slush
• AiCloser/Qwen2.5-32B-AGI
• AXCXEPT/EZO-Qwen2.5-32B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
    parameters:
      weight: 1.0
      density: 0.85
  - model: nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
    parameters:
      weight: 0.30
      density: 0.80
  - model: crestf411/Q2.5-32B-Slush
    parameters:
      weight: 0.25
      density: 0.80
  - model: huihui-ai/Qwen2.5-32B-Instruct-abliterated
    parameters:
      weight: 0.23
      density: 0.78
  - model: gctian/qwen2.5-32B-roleplay-zh
    parameters:
      weight: 0.22
      density: 0.75
  - model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
    parameters:
      weight: 0.20
      density: 0.73
  - model: jpacifico/Chocolatine-32B-Instruct-DPO-v1.2
    parameters:
      weight: 0.19
      density: 0.72
  - model: AXCXEPT/EZO-Qwen2.5-32B-Instruct
    parameters:
      weight: 0.18
      density: 0.72
  - model: AiCloser/Qwen2.5-32B-AGI
    parameters:
      weight: 0.15
      density: 0.68
  - model: huihui-ai/QwQ-32B-Preview-abliterated
    parameters:
      weight: 0.14
      density: 0.68

merge_method: dare_ties
base_model: Qwen/QwQ-32B-Preview
parameters:
  density: 0.84
  epsilon: 0.07
  lambda: 1.24
dtype: bfloat16
tokenizer_source: union