mergekit_config.yml

models:
  - model: tokyotech-llm/Swallow-7b-instruct-hf
    # no parameters necessary for base model
  - model: allenai/tulu-2-dpo-7b # follow user intent
    parameters:
      density: 1
      weight:
      - filter: mlp.down_proj
        value: [0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.10]
      - filter: mlp.gate_proj 
        value: [0.70, 0.10, 0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.10]
      - filter: mlp.up_proj
        value: [0.70, 0.10, 0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.10]
      - filter: self_attn
        value: [0.70, 0.45, 0.10, 0.45, 0.10, 0.45, 0.10, 0.45, 0.45]
      - value: 0 # fallback for rest of tensors.
merge_method: dare_ties
base_model: tokyotech-llm/Swallow-7b-instruct-hf
dtype: bfloat16
tokenizer_source: union
name: Superswallow-7b-v0.2-flavor
---
slices:
  - sources:
      - model: nitky/Superswallow-7b-baseline
        layer_range: [0, 32]
      - model: Superswallow-7b-v0.2-flavor
        layer_range: [0, 32]
merge_method: slerp
base_model: nitky/Superswallow-7b-baseline
parameters:
  t: # model stabilization
    - 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: bfloat16
name: Superswallow-7b-v0.2