merge_method: della_linear
base_model: Meta-Llama-3.1-70B-Instruct
models:
  - model: new-dawn-llama3-70b-32K-v1.0
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: up_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - value: 0
      density: 0.25
      epsilon: 0.05
      lambda: 1.0
  - model: Meta-Llama-3.1-70B-Instruct
    parameters:
        weight: 1.0
        density:
          - filter: v_proj
            value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
          - filter: o_proj
            value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
          - filter: up_proj
            value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
          - filter: gate_proj
            value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
          - filter: down_proj
            value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
          - value: 0.5
        epsilon:
          - filter: v_proj
            value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
          - filter: o_proj
            value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
          - filter: up_proj
            value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
          - filter: down_proj
            value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: float16
tokenizer_source: base