Modelpublic

Alelcv27/Qwen-7B-Breadcrumbs-v1

sourceHugging Faceupdated 8mo agoView on Hugging Face

0likes11downloads

Model Card

Qwen-7B-Breadcrumbs-v1

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

Merge Details

Merge Method

This model was merged using the Model Breadcrumbs merge method using Qwen/Qwen2.5-7B-Instruct as a base.

Models Merged

The following models were included in the merge:

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

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: Qwen/Qwen2.5-7B-Instruct
dtype: float16
merge_method: breadcrumbs
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 28]
        model: Alelcv27/Qwen2.5-7B-Code
        parameters:
          weight: 0.7
      - layer_range: [0, 28]
        model: Alelcv27/Qwen2.5-7B-Math-CoT
        parameters:
          weight: 0.9
      - layer_range: [0, 28]
        model: Qwen/Qwen2.5-7B-Instruct
parameters:
  density: 0.9
  gamma: 0.01
  normalize: 1.0