MrRobotoAI/Loki-v6

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 MrRobotoAI/test0011 as a base.

Models Merged

The following models were included in the merge:

• OmnicromsBrain/NeuralStar_Fusion-7B
• MrRobotoAI/Loki-v5.2
• OmnicromsBrain/Eros_Scribe-7b
• OmnicromsBrain/StoryFusion-7B
• MrRobotoAI/Frejya-0.8e
• OmnicromsBrain/EverythingBagel-DPO-7B
• OmnicromsBrain/ToppyCox-7B

Configuration

The following YAML configuration was used to produce this model:

 models:

  - model: OmnicromsBrain/Eros_Scribe-7b
    parameters:
      weight: 0.1
      density: 0.9
  - model: OmnicromsBrain/NeuralStar_Fusion-7B
    parameters:
      weight: 0.1
      density: 0.9
  - model: OmnicromsBrain/StoryFusion-7B
    parameters:
      weight: 0.1
      density: 0.9
  - model: OmnicromsBrain/EverythingBagel-DPO-7B
    parameters:
      weight: 0.1
      density: 0.9
  - model: OmnicromsBrain/ToppyCox-7B
    parameters:
      weight: 0.1
      density: 0.9
  - model: MrRobotoAI/Loki-v5.2
    parameters:
      weight: 0.25
      density: 0.9
  - model: MrRobotoAI/Frejya-0.8e
    parameters:
      weight: 0.25
      density: 0.9
      
 merge_method: dare_linear
 base_model: MrRobotoAI/test0011
 parameters:
  normalize: false
 dtype: float16