yamatazen/Shirayuki-SCE-9B

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using mergekit-community/Tigers-Abliterated-9B as a base.

Models Merged

The following models were included in the merge:

• AXCXEPT/EZO-Common-9B-gemma-2-it
• AXCXEPT/EZO-Humanities-9B-gemma-2-it
• ehristoforu/Gemma2-9B-it-psy10k-mental_health
• lemon07r/Gemma-2-Ataraxy-v4d-9B

Configuration

The following YAML configuration was used to produce this model:

base_model: mergekit-community/Tigers-Abliterated-9B
models:
  - model: lemon07r/Gemma-2-Ataraxy-v4d-9B
    parameters:
      weight: 1.0
  - model: ehristoforu/Gemma2-9B-it-psy10k-mental_health
    parameters:
      weight: 0.75
  - model: AXCXEPT/EZO-Common-9B-gemma-2-it
    parameters:
      weight: 0.5
  - model: AXCXEPT/EZO-Humanities-9B-gemma-2-it
    parameters:
      weight: 0.5
merge_method: sce
dtype: bfloat16
parameters:
  normalize: true
  select_topk: 0.5