zhiyuanhucs/qwen2.5-7b-merge-formula-0.33-sequence-0.33-backward-old-0.3

merge-formula-0.33-sequence-0.33-backward-old-0.3

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

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

• zhiyuanhucs/sequence-200-5
• zhiyuanhucs/formula-200-2
• zhiyuanhucs/backrward-reasoning-7B-level-2-0310

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: zhiyuanhucs/formula-200-2
    parameters:
      weight: 0.33
  - model: zhiyuanhucs/sequence-200-5
    parameters:
      weight: 0.33
  - model: zhiyuanhucs/backrward-reasoning-7B-level-2-0310
    parameters:
      weight: 0.33
merge_method: linear
dtype: float32