mergekit-community/MN-Sappho-c-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 Khetterman/AbominationScience-12B-v4 as a base.

Models Merged

The following models were included in the merge:

• LatitudeGames/Wayfarer-12B
• mistralai/Mistral-Nemo-Instruct-2407
• mergekit-community/MN-Sappho-b-12B
• mistralai/Mistral-Nemo-Base-2407
• inflatebot/MN-12B-Mag-Mell-R1
• mergekit-community/MN-Sappho-a-12B

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: Khetterman/AbominationScience-12B-v4
models:
  - model: Khetterman/AbominationScience-12B-v4
    parameters:
      weight: 1
  - model: LatitudeGames/Wayfarer-12B
    parameters:
      weight: 1
  - model: inflatebot/MN-12B-Mag-Mell-R1
    parameters:
      weight: 1
  - model: mergekit-community/MN-Sappho-b-12B
    parameters:
      weight: 1
  - model: mergekit-community/MN-Sappho-a-12B
    parameters:
      weight: 0.8
  - model: mistralai/Mistral-Nemo-Instruct-2407
    parameters:
      weight: 0.8
  - model: mistralai/Mistral-Nemo-Base-2407
    parameters:
      weight: 0.6
parameters:
  normalize: true