Best-Mix-Llama-3.1-8B

This is a test merge with all my favorite models

Best-Mix-Llama-3.1-8B is a merge of the following models using mergekit:

• DreadPoor/Aurora_faustus-8B-LINEAR
• bunnycore/Llama-3.1-8B-TitanFusion-Mix
• Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
• nvidia/OpenMath2-Llama3.1-8B
• vicgalle/Configurable-Llama-3.1-8B-Instruct

🧩 Configuration

models:
  - model: DreadPoor/Aurora_faustus-8B-LINEAR
    parameters:
      density: 0.8
      weight: 0.8
  - model: bunnycore/Llama-3.1-8B-TitanFusion-Mix
    parameters:
      density: 0.8
      weight: 0.8
  - model: Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
    parameters:
      density: 0.8
      weight: 0.8
  - model: nvidia/OpenMath2-Llama3.1-8B
    parameters:
      density: 0.8
      weight: 0.8
  - model: vicgalle/Configurable-Llama-3.1-8B-Instruct
    parameters:
      density: 0.8
      weight: 0.8


merge_method: ties
base_model: bunnycore/Llama-3.1-8B-TitanFusion-Mix
parameters:
  normalize: false
  int8_mask: true
dtype: float16