slices:
  - sources:
      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
        layer_range: [0, 8]
      - model: bamec66557/MISCHIEVOUS-12B-Mix_III_IV_V
        layer_range: [0, 8]
    parameters:
      t:
        - value: 0.72
  - sources:
      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
        layer_range: [8, 16]
      - model: bamec66557/MISCHIEVOUS-12B-Mix_III_IV_V
        layer_range: [8, 16]
    parameters:
      t:
        - value: [0.75, 0.85, 0.75]
  - sources:
      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
        layer_range: [16, 24]
      - model: bamec66557/MISCHIEVOUS-12B-Mix_III_IV_V
        layer_range: [16, 24]
    parameters:
      t:
        - value: [0.85, 1.0, 0.85]
        - filter: feed_forward
          value: [0.9, 1.0, 1.1]
  - sources:
      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
        layer_range: [24, 32]
      - model: bamec66557/MISCHIEVOUS-12B-Mix_III_IV_V
        layer_range: [24, 32]
    parameters:
      t:
        - value: [0.95, 1.0, 0.95]
  - sources:
      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
        layer_range: [32, 40]
      - model: bamec66557/MISCHIEVOUS-12B-Mix_III_IV_V
        layer_range: [32, 40]
    parameters:
      t:
        - value: 1.0
        - filter: self_attn
          value: [0.92, 1.0, 1.08]
merge_method: slerp
base_model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
regularization:
  - method: weight_clipping
    clip_range: [-0.04, 0.04]
postprocessing:
  - operation: gaussian_smoothing
    sigma: 0.9
  - operation: normalize
  - operation: quantize
    target_dtype: int8
dtype: bfloat16