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

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:

• grimjim/Llama-3-Oasis-v1-OAS-8B
• FPHam/L3-8B-Everything-COT
• chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
• flammenai/Mahou-1.2a-llama3-8B
• failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
• chujiezheng/LLaMA3-iterative-DPO-final-ExPO

Configuration

The following YAML configuration was used to produce this model:

models:

  - model: chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
    parameters:
      weight: 0.1429
      density: 0.9
  - model: chujiezheng/LLaMA3-iterative-DPO-final-ExPO
    parameters:
      weight: 0.1429
      density: 0.9
  - model: grimjim/Llama-3-Oasis-v1-OAS-8B
    parameters:
      weight: 0.1429
      density: 0.9
  - model: failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
    parameters:
      weight: 0.1429
      density: 0.9
  - model: flammenai/Mahou-1.2a-llama3-8B
    parameters:
      weight: 0.1429
      density: 0.9
  - model: FPHam/L3-8B-Everything-COT
    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