mergekit_config.yml

models:
  - model: Qwen/Qwen2.5-32B
  - model: Qwen/QwQ-32B
  - model: Qwen/Qwen2.5-Coder-32B-Instruct

merge_method: sce
base_model: Qwen/Qwen2.5-32B
parameters:
  select_topk: 0.6
  layers_weights:
    - pattern: "transformer.h.[0-9]|1[0-5]"  # Regex for layers 0-15
      value: [0.0, 0.7, 0.3]
    - pattern: "transformer.h.(1[6-9]|[2-4][0-9]|5[0-9])"  # Regex for layers 16-59
      value: [0.0, 0.9, 0.1]
    - pattern: "transformer.h.(6[0-3])"  # Regex for layers 60-63
      value: [0.0, 0.8, 0.2]
    - pattern: "lm_head"
      value: [0.0, 0.8, 0.2]
dtype: bfloat16