Aleteian/Avalon_7

merge

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

Merge Details

Merge Method

This model was merged using the della merge method using win10/Mistral-Nemo-abliterated-Nemo-Pro-v2 as a base.

Models Merged

The following models were included in the merge:

• ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
• DavidAU/MN-Dark-Planet-TITAN-12B
• elinas/Chronos-Gold-12B-1.0
• Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
• MarinaraSpaghetti/NemoMix-Unleashed-12B
• nothingiisreal/MN-12B-Celeste-V1.9
• TheDrummer/Rocinante-12B-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: win10/Mistral-Nemo-abliterated-Nemo-Pro-v2
    parameters:
      density: 0.11
      weight: 0.11

  - model: Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
    parameters:
      density: 0.9
      weight: 1.0
      
  - model: nothingiisreal/MN-12B-Celeste-V1.9
    parameters:
      density: 0.8
      weight: 1.0
      
  - model: elinas/Chronos-Gold-12B-1.0
    parameters:
      density: 0.8
      weight: 1.0
          
  - model: TheDrummer/Rocinante-12B-v1
    parameters:
      density: 0.8
      weight: 1.0
      
  - model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
    parameters:
      density: 0.8
      weight: 1.0

  - model: DavidAU/MN-Dark-Planet-TITAN-12B
    parameters:
      density: 0.8
      weight: 1.0      

  - model: MarinaraSpaghetti/NemoMix-Unleashed-12B
    parameters:
      density: 0.9
      weight: 1.0
      
      
merge_method: della
base_model: win10/Mistral-Nemo-abliterated-Nemo-Pro-v2

parameters:
  epsilon: 0.09
  lambda: 1.00
  int8_mask: true
  
dtype: float16