Theros/Qwen2.5-CreativeMix-7B

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 djuna/Q2.5-Fuppavy-7B as a base.

Models Merged

The following models were included in the merge:

• bunnycore/Qwen2.5-7B-HyperMix
• bunnycore/Qandora-2.5-7B-Creative
• edgerunner-ai/EdgeRunner-Command-Nested

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: djuna/Q2.5-Fuppavy-7B
    parameters:
      density: 0.5
      weight: 0.6
  - model: bunnycore/Qandora-2.5-7B-Creative
    parameters:
      density: 0.5
      weight: 0.4
  - model: bunnycore/Qwen2.5-7B-HyperMix
    parameters:
      density: 0.5
      weight: 0.4
  - model: edgerunner-ai/EdgeRunner-Command-Nested
    parameters:
      density: 0.5
      weight: 0.3

merge_method: dare_ties
base_model: djuna/Q2.5-Fuppavy-7B
parameters:
  normalize: false
  int8_mask: true
dtype: float16