bunnycore/Llama-3.1-8B-TitanFusion-Test

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using meta-llama/Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

• bunnycore/Llama-3.1-8B-TitanFusion-Mix
• vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
• Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
• bunnycore/Best-Mix-Llama-3.1-8B
• vicgalle/Configurable-Llama-3.1-8B-Instruct
• nvidia/OpenMath2-Llama3.1-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
    parameters:
      density: 0.7
      weight: 0.7
  - model: bunnycore/Best-Mix-Llama-3.1-8B
    parameters:
      density: 0.4
      weight: 0.3
  - model: vicgalle/Configurable-Llama-3.1-8B-Instruct
    parameters:
      density: 0.5
      weight: 0.5
  - model: nvidia/OpenMath2-Llama3.1-8B
    parameters:
      density: 0.5
      weight: 0.3
  - model: Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
    parameters:
      density: 0.8
      weight: 0.6
  - model: bunnycore/Llama-3.1-8B-TitanFusion-Mix
    parameters:
      density: 0.5
      weight: 0.4

merge_method: ties
base_model: meta-llama/Llama-3.1-8B
parameters:
  density: 1
  normalize: false
  int8_mask: true
dtype: float16