MrRobotoAI/Freyja-v4.92a-7b-ACADEMIC

merge

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

Merge Details

Merge Method

This model was merged using the linear DARE merge method using cognitivecomputations/Wizard-Vicuna-7B-Uncensored as a base.

Models Merged

The following models were included in the merge:

• hanzla/Wizard-Vicuna-7B-Uncensored-HF_REFINED
• ajibawa-2023/Uncensored-Jordan-7B
• MrRobotoAI/Freyja-v4.92-7b-Storywriter

Configuration

The following YAML configuration was used to produce this model:

 models:

  - model: MrRobotoAI/Freyja-v4.92-7b-Storywriter
    parameters:
      weight: 0.75
      density: 0.9
  - model: ajibawa-2023/Uncensored-Jordan-7B
    parameters:
      weight: 0.0833333333333333
      density: 0.9
  - model: hanzla/Wizard-Vicuna-7B-Uncensored-HF_REFINED
    parameters:
      weight: 0.0833333333333333
      density: 0.9
  - model: cognitivecomputations/Wizard-Vicuna-7B-Uncensored
    parameters:
      weight: 0.0833333333333333
      density: 0.9

 merge_method: dare_linear
 base_model: cognitivecomputations/Wizard-Vicuna-7B-Uncensored
 parameters:
  normalize: true
 dtype: float16