merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using unsloth/gemma-2-9b-it as a base.

Models Merged

The following models were included in the merge:

• anthracite-org/magnum-v3-9b-customgemma2
• rtzr/ko-gemma-2-9b-it
• flammenai/Mahou-1.3-gemma2-9B
• AlicanKiraz0/SenecaLLM_x_gemma-2-9b-CyberSecurity

Configuration

The following YAML configuration was used to produce this model:

base_model: unsloth/gemma-2-9b-it
merge_method: ties

slices:
  - sources:
      - model: unsloth/gemma-2-9b-it
        layer_range: [0, 42]
        parameters:
          density: 0.5
          weight: 0.3
      - model: rtzr/ko-gemma-2-9b-it
        layer_range: [0, 42]
        parameters:
          density: 0.45
          weight: 0.4
      - model: AlicanKiraz0/SenecaLLM_x_gemma-2-9b-CyberSecurity
        layer_range: [0, 42]
        parameters:
          density: 0.4
          weight: 0.1
      - model: anthracite-org/magnum-v3-9b-customgemma2
        layer_range: [0, 42]
        parameters:
          density: 0.45
          weight: 0.15
      - model: flammenai/Mahou-1.3-gemma2-9B
        layer_range: [0, 42]
        parameters:
          density: 0.5
          weight: 0.05
    merge_mode: cat
    dtype: bfloat16

parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16