mergekit_config.yml

slices:
  # Group 1
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [0, 0]
      - model: m-a-p/neo_7b
        layer_range: [3, 3]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [1, 1]
      - model: m-a-p/neo_7b
        layer_range: [3, 3]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [2, 2]
      - model: m-a-p/neo_7b
        layer_range: [3, 3]
  # Group 2
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [4, 4]
      - model: m-a-p/neo_7b
        layer_range: [7, 7]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [5, 5]
      - model: m-a-p/neo_7b
        layer_range: [7, 7]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [6, 6]
      - model: m-a-p/neo_7b
        layer_range: [7, 7]
  # Group 3
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [8, 8]
      - model: m-a-p/neo_7b
        layer_range: [11, 11]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [9, 9]
      - model: m-a-p/neo_7b
        layer_range: [11, 11]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [10, 10]
      - model: m-a-p/neo_7b
        layer_range: [11, 11]
  # Group 4
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [12, 12]
      - model: m-a-p/neo_7b
        layer_range: [15, 15]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [13, 13]
      - model: m-a-p/neo_7b
        layer_range: [15, 15]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [14, 14]
      - model: m-a-p/neo_7b
        layer_range: [15, 15]
  # Group 5
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [16, 16]
      - model: m-a-p/neo_7b
        layer_range: [19, 19]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [17, 17]
      - model: m-a-p/neo_7b
        layer_range: [19, 19]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [18, 18]
      - model: m-a-p/neo_7b
        layer_range: [19, 19]
  # Group 6
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [20, 20]
      - model: m-a-p/neo_7b
        layer_range: [23, 23]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [21, 21]
      - model: m-a-p/neo_7b
        layer_range: [23, 23]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [22, 22]
      - model: m-a-p/neo_7b
        layer_range: [23, 23]
  # Group 7 (last group)
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [24, 24]
      - model: m-a-p/neo_7b
        layer_range: [27, 27]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [25, 25]
      - model: m-a-p/neo_7b
        layer_range: [27, 27]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [26, 26]
      - model: m-a-p/neo_7b
        layer_range: [27, 27]
merge_method: slerp
base_model: m-a-p/neo_7b
parameters:
  t: 0.3333  # Apply 1/3 of the 4th layer to each of the previous 3 layers
dtype: bfloat16
output_path: ./merged_redistributed_neo_7b
model_config:
  num_hidden_layers: 21
  attention_bias: false
  attention_dropout: 0.0
  hidden_act: "silu"
  hidden_size: 3072
  intermediate_size: 24576
  num_attention_heads: 16
  num_key_value_heads: 16
  rms_norm_eps: 1e-05
  rope_theta: 10000.0
  use_cache: true