Modelpublic

tadashi-asaoka/merge-g1-SW

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes2downloads

Model Card

—augmxnt/shisa-gamma-7b-v1
—WizardLMTeam/WizardMath-7B-V1.1

🧩 Configuration

yaml

models:
  - model: augmxnt/shisa-gamma-7b-v1
    parameters:
      weight: 0.5
      density: 0.6
  - model: WizardLMTeam/WizardMath-7B-V1.1
    parameters:
      weight: 0.5
      density: 0.6
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
    normalize: false # optional
    allow_negative_weights: false # optional
dtype: bfloat16