digitalerbildungspartner/Marcoro14-7B-slerp

google/flan-t5-xl

Marcoro14-7B-slerp is a merge of the following models using mergekit:

• google/flan-t5-xl
• EmbeddedLLM/Mistral-7B-Merge-14-v0.1

🧩 Configuration

slices:
 slices:
      - sources:
          - model: google/flan-t5-xl
            layer_range: [0, 32]
          - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
            layer_range: [0, 32]
    merge_method: slerp
base_model: google/flan-t5-xl
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