Lllama-3-RedElixir-8B

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 NousResearch/Meta-Llama-3-8B as a base.

Models Merged

The following models were included in the merge:

• emnakamura/llama-3-MagicDolphin-8B
• Hastagaras/Jamet-8B-L3-MK.V-Blackroot
• flammenai/Mahou-1.2-llama3-8B
• nbeerbower/llama-3-spicy-abliterated-stella-8B
• Nitral-AI/Hathor_Stable-v0.2-L3-8B
• zeroblu3/NeuralPoppy-EVO-L3-8B
• hf-100/Llama-3-Spellbound-Instruct-8B-0.3

Configuration

The following YAML configuration was used to produce this model:

base_model: NousResearch/Meta-Llama-3-8B
dtype: bfloat16
merge_method: dare_ties
parameters:
  int8_mask: 1.0
slices:
- sources:
  - layer_range: [0, 32]
    model: NousResearch/Meta-Llama-3-8B
  - layer_range: [0, 32]
    model: nbeerbower/llama-3-spicy-abliterated-stella-8B
    parameters:
      density: 0.6
      weight: 0.22
  - layer_range: [0, 32]
    model: flammenai/Mahou-1.2-llama3-8B
    parameters:
      density: 0.6
      weight: 0.22
  - layer_range: [0, 32]
    model: hf-100/Llama-3-Spellbound-Instruct-8B-0.3
    parameters:
      density: 0.58
      weight: 0.14
  - layer_range: [0, 32]
    model: zeroblu3/NeuralPoppy-EVO-L3-8B
    parameters:
      density: 0.58
      weight: 0.14
  - layer_range: [0, 32]
    model: Nitral-AI/Hathor_Stable-v0.2-L3-8B
    parameters:
      density: 0.56
      weight: 0.1
  - layer_range: [0, 32]
    model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
    parameters:
      density: 0.56
      weight: 0.1
  - layer_range: [0, 32]
    model: emnakamura/llama-3-MagicDolphin-8B
    parameters:
      density: 0.55
      weight: 0.08