Qwen-7B-Ties-v1

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 Qwen/Qwen2.5-7B as a base.

Models Merged

The following models were included in the merge:

• Alelcv27/Qwen2.5-7B-Math-CoT
• Alelcv27/Qwen2.5-7B-Code

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-7B
dtype: float16
merge_method: ties
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 28]
        model: Alelcv27/Qwen2.5-7B-Math-CoT
        parameters:
          density: 0.3
          weight: 0.8
      - layer_range: [0, 28]
        model: Alelcv27/Qwen2.5-7B-Code
        parameters:
          density: 0.2
          weight: 0.5
      - layer_range: [0, 28]
        model: Qwen/Qwen2.5-7B
parameters:
  normalize: 1.0