mergekit_config.yml

merge_method: linear
dtype: float32
out_dtype: bfloat16
models:
  - model: NousResearch/Meta-Llama-3-8B
    parameters:
      weight: 1.0
  - model: NousResearch/Meta-Llama-3-8B-Instruct
    parameters:
      weight: 0.0
tokenizer:
  source: NousResearch/Meta-Llama-3-8B-Instruct
  tokens:
    <|start_header_id|>:
      source: NousResearch/Meta-Llama-3-8B-Instruct
      force: true
    <|end_header_id|>:
      source: NousResearch/Meta-Llama-3-8B-Instruct
      force: true
    <|eot_id|>:
      source: NousResearch/Meta-Llama-3-8B-Instruct
      force: true
    <|end_of_text|>:
      source: NousResearch/Meta-Llama-3-8B-Instruct
      force: true
    <|begin_of_text|>:
      source: NousResearch/Meta-Llama-3-8B-Instruct
      force: true