mergekit_config.yml

###############################
# llama-3-attenuated.yaml #
###############################

# Use: mergekit-yaml --clone-tensors ./llama-3-attenuated.yaml ./llama-3-attenuated
# See: https://github.com/arcee-ai/mergekit/issues/198 for discussion/reasoning behind this idea.

# ---

# The scale factor to use, eg: solve x^2 = 1/2 --> x = 1/sqrt(2) ≈ 0.7071067812
const_tag: &scale_factor 0.7071067812 # 1/sqrt(2)

# The filter parameters of a scaled block. 
attenuate-env: &attenuated_env
  parameters:
    scale:
      - filter: q_proj
        value: *scale_factor
      - filter: k_proj
        value: *scale_factor
      - value: 1.0

# ---

slices:

  ###########################
  # Block 1: miqu-1 [0, 16] #
  ###########################
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [0, 8] # The first 8 layers of Block 1 are not duplicated
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [8, 16] # The last 8 layers of Block 1 are are duplicated twice
      <<: *attenuated_env

  ###########################
  # Block 2: miqu-1 [8, 24] #
  ###########################
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [8, 24] # All the layers of Block 2 are are duplicated twice
      <<: *attenuated_env

  ##########################
  # Block 3: miqu-1 [16, 32] #
  ##########################
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [16, 24] # The first 8 layers of Block 3 are are duplicated twice
      <<: *attenuated_env
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [24, 32] # The last 8 layers of Block 3 are not duplicated

merge_method: passthrough
dtype: bfloat16