Kaoeiri/Qwenwify-32B-v2

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-instruct as a base.

Models Merged

The following models were included in the merge:

• huihui-ai/QwQ-32B-Preview-abliterated
• AXCXEPT/EZO-Qwen2.5-32B-Instruct
• AiCloser/Qwen2.5-32B-AGI
• crestf411/Q2.5-32B-Slush
• ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
• nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
• rombodawg/Rombos-LLM-V2.5-Qwen-32b
• unsloth/qwen2.5-32b-instruct + AITRICS-VD/moca_impression_dataset_0923-Qwen2.5-32B-Instruct-sft-lora
• EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2

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: rombodawg/Rombos-LLM-V2.5-Qwen-32b
    parameters:
      weight: 0.28
      density: 0.75
  - model: crestf411/Q2.5-32B-Slush
    parameters:
      weight: 0.25
      density: 0.74
  - model: AXCXEPT/EZO-Qwen2.5-32B-Instruct
    parameters:
      weight: 0.2
      density: 0.7
  - model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
    parameters:
      weight: 0.22
      density: 0.71
  - model: unsloth/qwen2.5-32b-instruct+AITRICS-VD/moca_impression_dataset_0923-Qwen2.5-32B-Instruct-sft-lora
    parameters:
      weight: 0.19
      density: 0.69
  - model: huihui-ai/QwQ-32B-Preview-abliterated
    parameters:
      weight: 0.16
      density: 0.67
  - model: nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
    parameters:
      weight: 0.12
      density: 0.6
  - model: AiCloser/Qwen2.5-32B-AGI
    parameters:
      weight: 0.14
      density: 0.66

merge_method: dare_ties
base_model: unsloth/qwen2.5-32b-instruct
parameters:
  density: 0.84
  epsilon: 0.07
  lambda: 1.24
dtype: bfloat16
tokenizer_source: union