mergekit_config.yml

slices:
  - sources:
      - model: djuna-test-lab/TEST-Ocerus-7B
        layer_range: [0, 16]
      - model: aws-prototyping/MegaBeam-Mistral-7B-512k
        layer_range: [0, 16]
    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: [0.6,0.35,0.5]
  - sources:
      - model: djuna-test-lab/TEST-Ocerus-7B
        layer_range: [16, 32]
      - model: aws-prototyping/MegaBeam-Mistral-7B-512k
        layer_range: [16, 32]
    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
merge_method: slerp
base_model: aws-prototyping/MegaBeam-Mistral-7B-512k
dtype: float32
out_dtype: bfloat16