bunnycore/Llama-3.1-8B-TitanFusion

merge

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 bunnycore/LLama-3.1-8B-Matrix as a base.

Models Merged

The following models were included in the merge:

• akjindal53244/Llama-3.1-Storm-8B
• bunnycore/HyperLlama-3.1-8B
• DreadPoor/Heart_Stolen-8B-Model_Stock
• refuelai/Llama-3-Refueled

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: DreadPoor/Heart_Stolen-8B-Model_Stock
    parameters:
      weight: 0.2
      density: 0.5
  - model: akjindal53244/Llama-3.1-Storm-8B
    parameters:
      weight: 0.5
      density: 0.5
  - model: refuelai/Llama-3-Refueled
    parameters:
      weight: 0.5
      density: 0.5
  - model: bunnycore/HyperLlama-3.1-8B
    parameters:
      weight: 0.3
      density: 0.5
  - model: bunnycore/LLama-3.1-8B-Matrix
    parameters:
      weight: 0.5
      density: 0.5
merge_method: dare_ties
base_model: bunnycore/LLama-3.1-8B-Matrix
dtype: bfloat16