Theros/Qwen2.5-ColdBrew-R1-test8

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using Theros/Qwen2.5-ColdBrew-R1-test4 as a base.

Models Merged

The following models were included in the merge:

• ZeroXClem/Qwen2.5-7B-Qandora-CySec
• bunnycore/Qwen-2.5-7B-Deep-Stock-v4
• ZeroXClem/Qwen2.5-7B-HomerCreative-Mix

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Theros/Qwen2.5-ColdBrew-R1-test4
    parameters:
      density: 0.6
      weight: 0.6
  - model: ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
    parameters:
      density: 0.5
      weight: 0.4
  - model: ZeroXClem/Qwen2.5-7B-Qandora-CySec
    parameters:
      density: 0.5
      weight: 0.4
  - model: bunnycore/Qwen-2.5-7B-Deep-Stock-v4
    parameters:
      density: 0.5
      weight: 0.5
merge_method: sce
base_model: Theros/Qwen2.5-ColdBrew-R1-test4
normalize: true
int8_mask: true
dtype: bfloat16
tokenizer_source: Theros/Qwen2.5-ColdBrew-R1-test4