SEC-MBX-7B-DPO

SEC-MBX-7B-DPO is a merge of the following models using mergekit:

• arcee-ai/sec-mistral-7b-instruct-1.2-epoch
• macadeliccc/MBX-7B-v3-DPO

🧩 Configuration

  slices:
    - sources:
        - model: arcee-ai/sec-mistral-7b-instruct-1.2-epoch
          layer_range: [0, 32]
        - model: macadeliccc/MBX-7B-v3-DPO
          layer_range: [0, 32]
  merge_method: slerp
  base_model: arcee-ai/sec-mistral-7b-instruct-1.2-epoch
  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