ECE-PRYMMAL-3B-SLERP_2-V1

ECE-PRYMMAL-3B-SLERP_2-V1 is a merge of the following models using mergekit:

• jpacifico/Chocolatine-3B-Instruct-DPO-Revised
• microsoft/Phi-3-mini-4k-instruct

🧩 Configuration

slices:
  - sources:
      - model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
        layer_range: [0, 32]
      - model: microsoft/Phi-3-mini-4k-instruct
        layer_range: [0, 32]
merge_method: slerp
base_model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
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