Edit model card

Patent-Instruct-Yi

Patent-Instruct-Yi is a merge of the following models using mergekit:

🧩 Configuration

  slices:
    - sources:
        - model: microsoft/Orca-2-7b
          layer_range: [0, 32]
        - model: arcee-ai/Patent-Instruct-7b
          layer_range: [0, 32]
  merge_method: slerp
  base_model: microsoft/Orca-2-7b
  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
Downloads last month
2
Safetensors
Model size
6.74B params
Tensor type
BF16
·