SvalTek/Qwen2.5-ColdBrew-Erratik-test

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using Theros/Qwen2.5-ColdBrew-R1 as a base.

Models Merged

The following models were included in the merge:

• SvalTek/Qwen2.5-ColdBrew-Erratik

Configuration

The following YAML configuration was used to produce this model:

name: Qwen2.5-ColdBrew
models:
  - model: Theros/Qwen2.5-ColdBrew-R1
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: SvalTek/Qwen2.5-ColdBrew-Erratik
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
merge_method: ties
base_model: Theros/Qwen2.5-ColdBrew-R1
parameters:
  normalize: true
  int8_mask: true
dtype: float16