mergekit_config.yml

merge_method: passthrough
dtype: bfloat16
slices:
# Original first 10 layers (L0-L9)
- sources:
  - layer_range: [0, 10]
    model: meta-llama/Llama-3.1-8B-Instruct

# Skip Dupe A of L10
# Original L10
- sources:
  - layer_range: [10, 11]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L10
- sources:
  - layer_range: [10, 11]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L11
- sources:
  - layer_range: [11, 12]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L11
- sources:
  - layer_range: [11, 12]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L11
- sources:
  - layer_range: [11, 12]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L12
- sources:
  - layer_range: [12, 13]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L12
- sources:
  - layer_range: [12, 13]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L12
- sources:
  - layer_range: [12, 13]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L13
- sources:
  - layer_range: [13, 14]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L13
- sources:
  - layer_range: [13, 14]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L13
- sources:
  - layer_range: [13, 14]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L14
- sources:
  - layer_range: [14, 15]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L14
- sources:
  - layer_range: [14, 15]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L14
- sources:
  - layer_range: [14, 15]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L15
- sources:
  - layer_range: [15, 16]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L15
- sources:
  - layer_range: [15, 16]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L15
- sources:
  - layer_range: [15, 16]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L16
- sources:
  - layer_range: [16, 17]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L16
- sources:
  - layer_range: [16, 17]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L16
- sources:
  - layer_range: [16, 17]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L17
- sources:
  - layer_range: [17, 18]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L17
- sources:
  - layer_range: [17, 18]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L17
- sources:
  - layer_range: [17, 18]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L18
- sources:
  - layer_range: [18, 19]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L18
- sources:
  - layer_range: [18, 19]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L18
- sources:
  - layer_range: [18, 19]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L19
- sources:
  - layer_range: [19, 20]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L19
- sources:
  - layer_range: [19, 20]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L19
- sources:
  - layer_range: [19, 20]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L20
- sources:
  - layer_range: [20, 21]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L20
- sources:
  - layer_range: [20, 21]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L20
- sources:
  - layer_range: [20, 21]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Dupe A of L21
- sources:
  - layer_range: [21, 22]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
# Original L21
- sources:
  - layer_range: [21, 22]
    model: meta-llama/Llama-3.1-8B-Instruct
# Dupe B of L21
- sources:
  - layer_range: [21, 22]
    model: meta-llama/Llama-3.1-8B-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0

# Original last 10 layers (L22-L31)
- sources:
  - layer_range: [22, 32]
    model: meta-llama/Llama-3.1-8B-Instruct