Modelpublic

Lolol857/Mephisto-JOSIE-AREX-4B

sourceHugging Faceupdated 2mo agoView on Hugging Face

2likes10downloads

Model Card

Mephisto-JOSIE-AREX-4B

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using /kaggle/working/josie-arex-slerp as a base.

Models Merged

The following models were included in the merge:

—CloudGoat/Mephisto-4B-0725

Configuration

The following YAML configuration was used to produce this model:

yaml


models:
  - model: /kaggle/working/josie-arex-slerp
    parameters:
      weight: 0.40
      density: 0.7
  - model: CloudGoat/Mephisto-4B-0725
    parameters:
      weight: 0.60
      density: 0.5
merge_method: dare_ties
base_model: /kaggle/working/josie-arex-slerp
parameters:
  int8_mask: true
  normalize: true
  density: 0.6
dtype: bfloat16