mega.yml

slices:
  - sources:
      - model: psmathur/orca_mini_v3_13b
        layer_range: [0, 40]
      - model: garage-bAInd/Platypus2-13B
        layer_range: [0, 40]
merge_method: slerp
base_model: psmathur/orca_mini_v3_13b
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: float16
name: gradient-slerp
---
models:
  - model: gradient-slerp
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: WizardLM/WizardMath-13B-V1.0
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model: TheBloke/Llama-2-13B-fp16
parameters:
  normalize: true
  int8_mask: true
dtype: float16
name: gradient-slerp-ties