Minerva-7B-Breadcrumbs-Math-French

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 sapienzanlp/Minerva-7B-instruct-v1.0 as a base.

Models Merged

The following models were included in the merge:

• Alelcv27/Minerva-7B-French-v2
• Alelcv27/Minerva-7B-Math-v2

Configuration

The following YAML configuration was used to produce this model:

base_model: sapienzanlp/Minerva-7B-instruct-v1.0
dtype: float16
merge_method: breadcrumbs
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 32]
        model: Alelcv27/Minerva-7B-French-v2
        parameters:
          weight: 0.8
      - layer_range: [0, 32]
        model: Alelcv27/Minerva-7B-Math-v2
        parameters:
          weight: 0.8
      - layer_range: [0, 32]
        model: sapienzanlp/Minerva-7B-instruct-v1.0
parameters:
  density: 0.9
  gamma: 0.01
  normalize: 1.0