merge

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

Merge Details

Merge Method

This model was merged using the task_swapping merge method using arcee-ai/Llama-3.1-SuperNova-Lite as a base.

Models Merged

The following models were included in the merge:

• DreadPoor/Heart_Stolen-8B-Model_Stock

Configuration

The following YAML configuration was used to produce this model:

base_model:
  model:
    path: arcee-ai/Llama-3.1-SuperNova-Lite
dtype: bfloat16
merge_method: task_swapping
slices:
- sources:
  - layer_range: [0, 32]
    model:
      model:
        path: DreadPoor/Heart_Stolen-8B-Model_Stock
    parameters:
      diagonal_offset: 2.0
      random_mask: 0.33
      random_mask_seed: 3181632.0
      weight: 1.0
  - layer_range: [0, 32]
    model:
      model:
        path: arcee-ai/Llama-3.1-SuperNova-Lite