README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - SciPhi/SciPhi-Mistral-7B-32k
  - cognitivecomputations/samantha-1.2-mistral-7b

Marcoro14-7B-slerp

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

• SciPhi/SciPhi-Mistral-7B-32k
• cognitivecomputations/samantha-1.2-mistral-7b

🧩 Configuration

slices:
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [0, 32]
      - model: cognitivecomputations/samantha-1.2-mistral-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: SciPhi/SciPhi-Mistral-7B-32k
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