Poetic-Rune-12B

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

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using mistralai/Mistral-Nemo-Instruct-2407 as a base.

Models Merged

The following models were included in the merge:

• LatitudeGames/Wayfarer-2-12B
• Epiculous/Violet_Twilight-v0.2
• inflatebot/MN-12B-Mag-Mell-R1
• cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: LatitudeGames/Wayfarer-2-12B
    parameters:
      weight: 0.15
      density: 0.7
      epsilon: 0.1
  - model: inflatebot/MN-12B-Mag-Mell-R1
    parameters:
      weight: 0.3
      density: 0.6
      epsilon: 0.3
  - model: Epiculous/Violet_Twilight-v0.2
    parameters:
      weight: 0.3
      density: 0.6
      epsilon: 0.3
  - model: cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO
    parameters:
      weight: 0.15
      density: 0.65
      epsilon: 0.1
merge_method: della_linear
base_model: mistralai/Mistral-Nemo-Instruct-2407
parameters:
  lambda: 1
  normalize: true
dtype: bfloat16
tokenizer:
 source: union