mido

mido is a merge of the following models using mergekit:

• mlabonne/NeuralHermes-2.5-Mistral-7B
• mistralai/Mistral-7B-Instruct-v0.2

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    # no parameters necessary for base model
  - model: mlabonne/NeuralHermes-2.5-Mistral-7B
    parameters:
      density: 0.5
      weight: 0.5
  - model: mistralai/Mistral-7B-Instruct-v0.2
    parameters:
      density: 0.5
      weight: 0.3
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  normalize: true
dtype: float16