Kaoeiri/Qwenwify-32B-v2.6

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 unsloth/qwen2.5-32b as a base.

Models Merged

The following models were included in the merge:

• ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
• AXCXEPT/EZO-Qwen2.5-32B-Instruct
• AiCloser/Qwen2.5-32B-AGI
• huihui-ai/QwQ-32B-Preview-abliterated
• crestf411/Q2.5-32B-Slush
• rombodawg/Rombos-LLM-V2.5-Qwen-32b
• EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
• nbeerbower/Qwen2.5-Gutenberg-Doppel-32B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
    parameters:
      weight: 0.9
      density: 0.82
  - model: AiCloser/Qwen2.5-32B-AGI
    parameters:
      weight: 0.24
      density: 0.76
  - model: crestf411/Q2.5-32B-Slush
    parameters:
      weight: 0.21
      density: 0.73
  - model: AXCXEPT/EZO-Qwen2.5-32B-Instruct
    parameters:
      weight: 0.18
      density: 0.71
  - model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
    parameters:
      weight: 0.19
      density: 0.72
  - model: huihui-ai/QwQ-32B-Preview-abliterated
    parameters:
      weight: 0.12
      density: 0.65
  - model: nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
    parameters:
      weight: 0.14
      density: 0.64
  - model: rombodawg/Rombos-LLM-V2.5-Qwen-32b
    parameters:
      weight: 0.11
      density: 0.65

merge_method: dare_ties
base_model: unsloth/qwen2.5-32b
parameters:
  density: 0.83
  epsilon: 0.06
  lambda: 1.22
dtype: bfloat16
tokenizer_source: union