MrRobotoAI/Freyja-v4.94e-7b-GENERAL

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 luvGPT/mistral-7b-uncensored as a base.

Models Merged

The following models were included in the merge:

• Undi95/MistRP-Dolphin-7B
• cognitivecomputations/dolphin-llama2-7b
• cognitivecomputations/dolphin-2.2.1-mistral-7b
• jdqqjr/vicuna-7b-v1.5-uncensored
• MrRobotoAI/Freyja-v4.95-7b-GENERAL
• Weyaxi/Dolphin-Nebula-7B

Configuration

The following YAML configuration was used to produce this model:

 models:
  
  - model: MrRobotoAI/Freyja-v4.95-7b-GENERAL
    parameters:
      weight: 0.6
      density: 0.9
  - model: cognitivecomputations/dolphin-2.2.1-mistral-7b
    parameters:
      weight: 0.08
      density: 0.9
  - model: Weyaxi/Dolphin-Nebula-7B
    parameters:
      weight: 0.08
      density: 0.9
  - model: Undi95/MistRP-Dolphin-7B
    parameters:
      weight: 0.08
      density: 0.9
  - model: cognitivecomputations/dolphin-llama2-7b
    parameters:
      weight: 0.08
      density: 0.9
  - model: jdqqjr/vicuna-7b-v1.5-uncensored
    parameters:
      weight: 0.08
      density: 0.9
  
 merge_method: dare_linear
 base_model: luvGPT/mistral-7b-uncensored
 parameters:
  normalize: true
 dtype: float16