Bio_swallow

Bio_swallow is a merge of the following models using mergekit:

• tokyotech-llm/Swallow-MS-7b-v0.1
• BioMistral/BioMistral-7B

🧩 Configuration

slices:
  - sources:
      - model: tokyotech-llm/Swallow-MS-7b-v0.1
        layer_range: [0, 32]
      - model: BioMistral/BioMistral-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: BioMistral/BioMistral-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