mixtral-ties

For experimental purposes. Probably not very good.

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

• monology/mixtral-slerp0
• monology/mixtral-slerp5
• monology/mixtral-slerp6
• monology/mixtral-slerp2
• monology/mixtral-slerp3
• monology/mixtral-slerp7
• monology/mixtral-slerp4
• monology/mixtral-slerp1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: monology/mixtral-slerp0
    parameters:
      density: 0.5
      weight: 0.1
  - model: monology/mixtral-slerp1
    parameters:
      density: 0.5
      weight: 0.1
  - model: monology/mixtral-slerp2
    parameters:
      density: 0.5
      weight: 0.1
  - model: monology/mixtral-slerp3
    parameters:
      density: 0.5
      weight: 0.1
  - model: monology/mixtral-slerp4
    parameters:
      density: 0.5
      weight: 0.1
  - model: monology/mixtral-slerp5
    parameters:
      density: 0.5
      weight: 0.1
  - model: monology/mixtral-slerp6
    parameters:
      density: 0.5
      weight: 0.1
  - model: monology/mixtral-slerp7
    parameters:
      density: 0.5
      weight: 0.1
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  normalize: true
dtype: float16