MrRobotoAI/llama3-8B-Special-Dark-v3.1.1a

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 MrRobotoAI/llama3-8B-Special-Dark-v2.0 as a base.

Models Merged

The following models were included in the merge:

• abacusai/Llama-3-Smaug-8B
• ajibawa-2023/Scarlett-Llama-3-8B-v1.0
• ChaoticNeutrals/Templar_v1_8B
• chargoddard/prometheus-2-llama-3-8b
• ChaoticNeutrals/Hathor_RP-v.01-L3-8B
• Blackroot/Llama-3-Gamma-Twist

Configuration

The following YAML configuration was used to produce this model:

models:

  - model: abacusai/Llama-3-Smaug-8B
    parameters:
      weight: 0.1429
      density: 0.9
  - model: ajibawa-2023/Scarlett-Llama-3-8B-v1.0
    parameters:
      weight: 0.1429
      density: 0.9
  - model: Blackroot/Llama-3-Gamma-Twist
    parameters:
      weight: 0.1429
      density: 0.9
  - model: ChaoticNeutrals/Hathor_RP-v.01-L3-8B
    parameters:
      weight: 0.1429
      density: 0.9
  - model: ChaoticNeutrals/Templar_v1_8B
    parameters:
      weight: 0.1429
      density: 0.9
  - model: chargoddard/prometheus-2-llama-3-8b
    parameters:
      weight: 0.1429
      density: 0.9
  - model: MrRobotoAI/llama3-8B-Special-Dark-v2.0
    parameters:
      weight: 0.1429
      density: 0.9

merge_method: dare_ties
base_model: MrRobotoAI/llama3-8B-Special-Dark-v2.0
parameters:
  normalize: true
  int8_mask: true
dtype: float16