mergekit-community/MN-Hekate-Limenoskopos-12B

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using mergekit-community/MN-Hekate-Geneteira-12B as a base.

Models Merged

The following models were included in the merge:

• mergekit-community/MN-Hekate-Anassa-17B
• mergekit-community/MN-Hekate-Damnomeneia-17B
• mergekit-community/MN-Hekate-Limenoskopos-17B
• mergekit-community/MN-Hekate-Daidalos-17B

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mergekit-community/MN-Hekate-Geneteira-12B
slices:
  - sources:
    - model: mergekit-community/MN-Hekate-Geneteira-12B
      layer_range: [0, 12]

  - sources:
    - model: mergekit-community/MN-Hekate-Geneteira-12B
      layer_range: [12, 16]
    - model: mergekit-community/MN-Hekate-Anassa-17B
      layer_range: [12, 16]
    - model: mergekit-community/MN-Hekate-Daidalos-17B
      layer_range: [12, 16]
    - model: mergekit-community/MN-Hekate-Damnomeneia-17B
      layer_range: [12, 16]
    - model: mergekit-community/MN-Hekate-Limenoskopos-17B
      layer_range: [12, 16]

  - sources:
    - model: mergekit-community/MN-Hekate-Geneteira-12B
      layer_range: [16, 20]
    - model: mergekit-community/MN-Hekate-Anassa-17B
      layer_range: [20, 24]
    - model: mergekit-community/MN-Hekate-Daidalos-17B
      layer_range: [20, 24]
    - model: mergekit-community/MN-Hekate-Damnomeneia-17B
      layer_range: [20, 24]
    - model: mergekit-community/MN-Hekate-Limenoskopos-17B
      layer_range: [20, 24]

  - sources:
    - model: mergekit-community/MN-Hekate-Geneteira-12B
      layer_range: [20, 28]
    - model: mergekit-community/MN-Hekate-Anassa-17B
      layer_range: [24, 32]
    - model: mergekit-community/MN-Hekate-Anassa-17B
      layer_range: [36, 44]
    - model: mergekit-community/MN-Hekate-Daidalos-17B
      layer_range: [24, 32]
    - model: mergekit-community/MN-Hekate-Daidalos-17B
      layer_range: [36, 44]
    - model: mergekit-community/MN-Hekate-Damnomeneia-17B
      layer_range: [24, 32]
    - model: mergekit-community/MN-Hekate-Damnomeneia-17B
      layer_range: [36, 44]
    - model: mergekit-community/MN-Hekate-Limenoskopos-17B
      layer_range: [24, 32]
    - model: mergekit-community/MN-Hekate-Limenoskopos-17B
      layer_range: [36, 44]

  - sources:
    - model: mergekit-community/MN-Hekate-Geneteira-12B
      layer_range: [28, 32]
    - model: mergekit-community/MN-Hekate-Anassa-17B
      layer_range: [32, 36]
    - model: mergekit-community/MN-Hekate-Anassa-17B
      layer_range: [44, 48]
    - model: mergekit-community/MN-Hekate-Daidalos-17B
      layer_range: [32, 36]
    - model: mergekit-community/MN-Hekate-Daidalos-17B
      layer_range: [44, 48]
    - model: mergekit-community/MN-Hekate-Damnomeneia-17B
      layer_range: [32, 36]
    - model: mergekit-community/MN-Hekate-Damnomeneia-17B
      layer_range: [44, 48]
    - model: mergekit-community/MN-Hekate-Limenoskopos-17B
      layer_range: [32, 36]
    - model: mergekit-community/MN-Hekate-Limenoskopos-17B
      layer_range: [44, 48]

  - sources:
    - model: mergekit-community/MN-Hekate-Geneteira-12B
      layer_range: [32, 40]
    - model: mergekit-community/MN-Hekate-Anassa-17B
      layer_range: [48, 56]
    - model: mergekit-community/MN-Hekate-Daidalos-17B
      layer_range: [48, 56]
    - model: mergekit-community/MN-Hekate-Damnomeneia-17B
      layer_range: [48, 56]
      parameters:
        weight: 1.5
    - model: mergekit-community/MN-Hekate-Limenoskopos-17B
      layer_range: [48, 56]
      parameters:
        weight: 2