mergekit_config.yml

base_model: unsloth/Meta-Llama-3.1-8B-Instruct
dtype: bfloat16
merge_method: dare_ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
  random_seed: 145.0
slices:
- sources:
  - layer_range: [0, 32]
    model: unsloth/Llama-3.1-Storm-8B
    parameters:
      density: 0.94
      weight: 0.35
  - layer_range: [0, 32]
    model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      density: 0.92
      weight: 0.2
  - layer_range: [0, 32]
    model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
    parameters:
      density: 0.91
      weight: 0.2
  - layer_range: [0, 32]
    model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
    parameters:
      density: 0.93
      weight: 0.19
  - layer_range: [0, 32]
    model: allenai/Llama-3.1-Tulu-3-8B
    parameters:
      density: 0.92
      weight: 0.03
  - layer_range: [0, 32]
    model: FreedomIntelligence/HuatuoGPT-o1-8B
    parameters:
      density: 0.92
      weight: 0.03
  - layer_range: [0, 32]
    model: unsloth/Meta-Llama-3.1-8B-Instruct
tokenizer:
  tokens:
    <pad>:
      source:
        kind: model_token
        model: unsloth/Meta-Llama-3.1-8B-Instruct
        token: <|finetune_right_pad_id|>
    <|begin_of_text|>:
      force: true
      source: unsloth/Meta-Llama-3.1-8B-Instruct
    <|eot_id|>:
      force: true
      source: unsloth/Meta-Llama-3.1-8B-Instruct
    <|finetune_right_pad_id|>:
      force: true
      source: unsloth/Meta-Llama-3.1-8B-Instruct