MrRobotoAI/llama3-8B-Special-Dark-RP1

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:

• MrRobotoAI/llama3-8B-Special-Dark-v3.1.1w
• MrRobotoAI/Unholy-Thoth-8B-v2
• MrRobotoAI/llama3-8B-Special-Dark-v3.1.1u
• MrRobotoAI/llama3-8B-Special-Dark-v3.1.1v

Configuration

The following YAML configuration was used to produce this model:

models:

  - model: MrRobotoAI/llama3-8B-Special-Dark-v3.1.1w
    parameters:
      weight: 0.2
      density: 0.9
  - model: MrRobotoAI/llama3-8B-Special-Dark-v3.1.1v
    parameters:
      weight: 0.2
      density: 0.9
  - model: MrRobotoAI/llama3-8B-Special-Dark-v3.1.1u
    parameters:
      weight: 0.25
      density: 0.9
  - model: MrRobotoAI/Unholy-Thoth-8B-v2
    parameters:
      weight: 0.25
      density: 0.9
  - model: MrRobotoAI/llama3-8B-Special-Dark-v2.0
    parameters:
      weight: 0.1
      density: 0.9

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