mistral-7b-shisa-7b-v1

mistral-7b-shisa-7b-v1 is a merge of the following models using mergekit:

• ajibawa-2023/Code-Mistral-7B
• augmxnt/shisa-7b-v1

🧩 Configuration

slices:
  - sources:
      - model: ajibawa-2023/Code-Mistral-7B
        layer_range: [0, 32]
      - model: augmxnt/shisa-7b-v1
        layer_range: [0, 32]
merge_method: slerp
base_model: ajibawa-2023/Code-Mistral-7B
parameters:
  t:
    - 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
dtype: bfloat16