storyteller

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using LatitudeGames/Wayfarer-2-12B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: LatitudeGames/Wayfarer-2-12B
dtype: bfloat16
merge_method: dare_ties
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 40]
        model: LatitudeGames/Wayfarer-2-12B
      - layer_range: [0, 40]
        model: LatitudeGames/Muse-12B+jtatman/mistral_nemo_12b_reasoning_psychology_lora
        parameters:
          density: 0.9
          weight: 1.0
      - layer_range: [0, 40]
        model: aixonlab/Zinakha-12b
        parameters:
          density: 0.7
          weight: 0.6
      - layer_range: [0, 40]
        model: inflatebot/MN-12B-Mag-Mell-R1
        parameters:
          density: 0.7
          weight: 0.6
parameters:
  normalize: 1.0
tokenizer: {}