README.md

metadata

pipeline_tag: text-generation
tags:
  - mistral
  - merge
license: cc-by-4.0

Model Card for Moko-DARE

Part of a merge method experiment.

.yaml file for mergekit

models:
  - model: Open-Orca/Mistral-7B-OpenOrca
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: akjindal53244/Mistral-7B-v0.1-Open-Platypus
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
  - model: WizardLM/WizardMath-7B-V1.1
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  normalize: true
  int8_mask: true
dtype: float16