MrRobotoAI/test002a

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 MrRobotoAI/Test001a as a base.

Models Merged

The following models were included in the merge:

• jdqwoi/TooManyMixRolePlay-7B-Story_V3.5
• kasper52786/StoryWeaver-7b-Instruct-v0.1
• MaziyarPanahi/Mistral-7B-claude-instruct-Mistral-7B-Instruct-v0.2-slerp
• KnutJaegersberg/Mistral-7B-EssayWriter
• tdh87/StoryTeller7b-meh
• ajibawa-2023/General-Stories-Mistral-7B
• luozhuanggary/GOAT-v0.2-Mistral-7B-Claude
• scribis/Fantastica-7b-Instruct-0.2-Italian_merged
• ajibawa-2023/Young-Children-Storyteller-Mistral-7B

Configuration

The following YAML configuration was used to produce this model:

### This the config.yml for ABC_Books/test002 ###
 models:

  - model: KnutJaegersberg/Mistral-7B-EssayWriter
    parameters:
      weight: 0.1
      density: 0.9
  - model: MaziyarPanahi/Mistral-7B-claude-instruct-Mistral-7B-Instruct-v0.2-slerp
    parameters:
      weight: 0.1
      density: 0.9
  - model: ajibawa-2023/General-Stories-Mistral-7B
    parameters:
      weight: 0.1
      density: 0.9
  - model: ajibawa-2023/Young-Children-Storyteller-Mistral-7B
    parameters:
      weight: 0.1
      density: 0.9
  - model: jdqwoi/TooManyMixRolePlay-7B-Story_V3.5
    parameters:
      weight: 0.1
      density: 0.9
  - model: kasper52786/StoryWeaver-7b-Instruct-v0.1
    parameters:
      weight: 0.1
      density: 0.9
  - model: luozhuanggary/GOAT-v0.2-Mistral-7B-Claude
    parameters:
      weight: 0.1
      density: 0.9
  - model: scribis/Fantastica-7b-Instruct-0.2-Italian_merged
    parameters:
      weight: 0.1
      density: 0.9
  - model: tdh87/StoryTeller7b-meh
    parameters:
      weight: 0.1
      density: 0.9
  - model: MrRobotoAI/Test001a
    parameters:
      weight: 0.1
      density: 0.9

 merge_method: dare_ties
  ### Now this model best exemplifies the closest match to all of the features needed in the final model. So it now becomes the base model for merges ###
 base_model: MrRobotoAI/Test001a
 parameters:
  normalize: true
  int8_mask: true
 dtype: float16