README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - Gryphe/Pantheon-RP-1.5-12b-Nemo
  - anthracite-org/magnum-12b-v2
  - grimjim/mistralai-Mistral-Nemo-Base-2407

NemoMerge-12B-DellaV1b

NemoMerge-12B-DellaV1b is a merge of the following models using mergekit:

• Gryphe/Pantheon-RP-1.5-12b-Nemo
• anthracite-org/magnum-12b-v2
• grimjim/mistralai-Mistral-Nemo-Base-2407

🧩 Configuration

models:
  - model: Gryphe/Pantheon-RP-1.5-12b-Nemo
    parameters:
      weight: 0.33
      density: 0.7
  - model: anthracite-org/magnum-12b-v2
    parameters:
      weight: 0.33
      density: 0.7
  - model: grimjim/mistralai-Mistral-Nemo-Base-2407
    parameters:
      weight: 0.33
      density: 0.65
merge_method: della
base_model: grimjim/mistralai-Mistral-Nemo-Base-2407
parameters:
  int8_mask: true
  normalize: true
  epsilon: 0.05  
  lambda: 1.0   
dtype: bfloat16