mergekit_config.yml

merge_method: linear
parameters:
  weight: 1.0
slices:
- sources:
  - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
    layer_range: [0, 16]
- sources:
  - model: cyberagent/Llama-3.1-70B-Japanese-Instruct-2407
    layer_range: [8, 24]
- sources:
  - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
    layer_range: [17, 32]
- sources:
  - model: cyberagent/Llama-3.1-70B-Japanese-Instruct-2407
    layer_range: [25, 40]
- sources:
  - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
    layer_range: [33, 48]
- sources:
  - model: cyberagent/Llama-3.1-70B-Japanese-Instruct-2407
    layer_range: [41, 56]
- sources:
  - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
    layer_range: [49, 64]
- sources:
  - model: cyberagent/Llama-3.1-70B-Japanese-Instruct-2407
    layer_range: [57, 72]
- sources:
  - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
    layer_range: [65, 80]
dtype: float16
tokenizer_source: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF