mergekit_config.yml

const_tag:
  - &SFU 0.7071067812  # Upper scaling factor (1/sqrt(2))
  - &SFL 0.85          # Lower scaling factor
  - &SFMLP 0.8         # MLP scaling factor

attenuate-env-lower: &attenuated_env_lower
  parameters:
    scale:
      - filter: q_proj
        value: *SFL
      - filter: k_proj
        value: *SFL
      - filter: v_proj
        value: *SFL
      - filter: o_proj
        value: *SFL
      - filter: gate_proj
        value: *SFMLP
      - filter: up_proj
        value: *SFMLP
      - filter: down_proj
        value: *SFMLP

attenuate-env-upper: &attenuated_env_upper
  parameters:
    scale:
      - filter: q_proj
        value: *SFU
      - filter: k_proj
        value: *SFU
      - filter: v_proj
        value: *SFU
      - filter: o_proj
        value: *SFU
      - filter: gate_proj
        value: *SFMLP
      - filter: up_proj
        value: *SFMLP
      - filter: down_proj
        value: *SFMLP

slices:
  # Preserve input layers
  - sources:
      - model: SvalTek/ColdBrew-Aphid
        layer_range: [0, 12]

  # Early Expansion (Duplicate Twice)
  - sources:
      - model: SvalTek/ColdBrew-Aphid
        layer_range: [13, 15]
  - sources:
      - model: SvalTek/ColdBrew-Aphid
        layer_range: [13, 15]
        <<: *attenuated_env_lower
  - sources:
      - model: SvalTek/ColdBrew-Aphid
        layer_range: [13, 15]
        <<: *attenuated_env_lower

  # Late Expansion (Duplicate Twice)
  - sources:
      - model: SvalTek/ColdBrew-Aphid
        layer_range: [15, 18]
  - sources:
      - model: SvalTek/ColdBrew-Aphid
        layer_range: [15, 18]
        <<: *attenuated_env_upper
  - sources:
      - model: SvalTek/ColdBrew-Aphid
        layer_range: [15, 18]
        <<: *attenuated_env_upper

  # Preserve output layers
  - sources:
      - model: SvalTek/ColdBrew-Aphid
        layer_range: [19, 27]

merge_method: passthrough
dtype: bfloat16
parameters:
  normalize: true
  int8_mask: true