#--DUAL MODEL MERGE SETUP---

# More buffer for the start and end layers (20 non duplicated as apposed to 10)
# Merging two faves Undi95/PsyMedRP-v1-20B and Undi95/PsyMedRP-v1-20B



# The models we are going to use.
const_tag: &BASE_MODEL Undi95/PsyMedRP-v1-20B
const_tag: &MODEL1 Undi95/MXLewd-L2-20B
const_tag: &MODEL2 Undi95/PsyMedRP-v1-20B

# The amount to scale the contribution to the residual stream (to hopefully reduce overshoot).
const_tag: &RESIDUAL_SCALE_FACTOR 0.71 # back to 0.7

model1-filter-env: &MODEL1_FILTER_ENV
  parameters:
    scale:
      - filter: down_proj
        value: *RESIDUAL_SCALE_FACTOR
      - value: 1.0

model2-filter-env: &MODEL2_FILTER_ENV
  parameters:
    scale:
      - filter: down_proj
        value: *RESIDUAL_SCALE_FACTOR
      - value: 1.0

slices:

  # The first 20 layers are not duplicated.
  - sources:
    - model: *BASE_MODEL
      layer_range: [0, 20]

  - sources:
    - model: *MODEL1
      layer_range: [20, 21]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [20, 21]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [21, 22]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [21, 22]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [22, 23]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [22, 23]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [23, 24]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [23, 24]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [24, 25]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [24, 25]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [25, 26]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [25, 26]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [26, 27]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [26, 27]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [27, 28]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [27, 28]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [28, 29]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [28, 29]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [29, 30]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [29, 30]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [30, 31]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [30, 31]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [31, 32]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [31, 32]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [32, 33]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [32, 33]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [33, 34]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [33, 34]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [34, 35]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [34, 35]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [35, 36]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [35, 36]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [36, 37]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [36, 37]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [37, 38]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [37, 38]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [38, 39]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [38, 39]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [39, 40]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [39, 40]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [40, 41]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [40, 41]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [41, 42]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [41, 42]
      <<: *MODEL2_FILTER_ENV
  - sources:
    - model: *MODEL1
      layer_range: [42, 43]
      <<: *MODEL1_FILTER_ENV
  - sources:
    - model: *MODEL2
      layer_range: [42, 43]
      <<: *MODEL2_FILTER_ENV
  

# The last 20 layers are not duplicated.
  - sources:
    - model: *BASE_MODEL
      layer_range: [42, 62]

merge_method: passthrough
dtype: bfloat16