nocudaexe/Dark-Waifu-7b

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using mlabonne/AlphaMonarch-7B as a base.

Models Merged

The following models were included in the merge:

• TeeZee/DarkSapling-7B-v2.0
• Test157t/Kunocchini-7b-128k-test
• NeverSleep/Noromaid-7B-0.4-DPO
• Endevor/InfinityRP-v1-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mlabonne/AlphaMonarch-7B
    # No parameters necessary for base model
  - model: Test157t/Kunocchini-7b-128k-test
    parameters:
      density: 0.43
      weight: 0.4
  - model: TeeZee/DarkSapling-7B-v2.0
    parameters:
      density: 0.23
      weight: 0.3
  - model: NeverSleep/Noromaid-7B-0.4-DPO
    parameters:
      density: 0.23
      weight: 0.3
  - model: Endevor/InfinityRP-v1-7B
    parameters:
      density: 0.2
      weight: 0.3
merge_method: dare_ties
base_model: mlabonne/AlphaMonarch-7B
parameters:
  int8_mask: true
dtype: bfloat16