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

merge

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• grimjim/Llama-3-Perky-Pat-Instruct-8B
• FPHam/L3-8B-Everything-COT
• flammenai/Mahou-1.2a-llama3-8B
• chujiezheng/LLaMA3-iterative-DPO-final-ExPO
• failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
• lemon07r/Llama-3-RedMagic2-8B
• disinfozone/Disinfo4_mistral-ft-optimized-1218

Configuration

The following YAML configuration was used to produce this model:

models:

  - model: chujiezheng/LLaMA3-iterative-DPO-final-ExPO
    parameters:
      weight: 1.0
  - model: disinfozone/Disinfo4_mistral-ft-optimized-1218
    parameters:
      weight: 1.0
  - model: failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
    parameters:
      weight: 1.0
  - model: flammenai/Mahou-1.2a-llama3-8B
    parameters:
      weight: 1.0
  - model: FPHam/L3-8B-Everything-COT
    parameters:
      weight: 1.0
  - model: lemon07r/Llama-3-RedMagic2-8B
    parameters:
      weight: 1.0
  - model: grimjim/Llama-3-Perky-Pat-Instruct-8B
    parameters:
      weight: 1.0

merge_method: linear
dtype: float16