README.md

metadata

base_model:
  - smelborp/MixtralOrochi8x7B
library_name: transformers
tags:
  - mergekit
  - merge

maid-yuzu-v5-mix

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

This model was created because I was curious about whether the 8X7B model created randomly by the user would be merged with other existing 8x7b models.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• ../maid-yuzu-v5
• smelborp/MixtralOrochi8x7B

Configuration

The following YAML configuration was used to produce this model:

base_model:
  model:
    path: ../maid-yuzu-v5
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 32]
    model:
      model:
        path: smelborp/MixtralOrochi8x7B
  - layer_range: [0, 32]
    model:
      model:
        path: ../maid-yuzu-v5