Azazelle/L3-Dumb-Peter-Griffin-8b

merge

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

Merge Details

Merge Method

This model was merged using the breadcrumbs_ties merge method using failspy/Llama-3-8B-Instruct-MopeyMule as a base.

Models Merged

The following models were included in the merge:

• Sao10K/L3-8B-Stheno-v3.1
• openlynn/Llama-3-Soliloquy-8B-v2
• Nitral-AI/Poppy_Porpoise-1.0-L3-8B
• NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
• flammenai/Mahou-1.0-llama3-8B
• Hastagaras/UltimateANJIR-8B-L3-Blackroot
• TheSkullery/llama-3-cat-8b-instruct-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: failspy/Llama-3-8B-Instruct-MopeyMule
  - model: flammenai/Mahou-1.0-llama3-8B # 7/10
    parameters:
      density: 0.4
      weight: 0.14
  - model: TheSkullery/llama-3-cat-8b-instruct-v1 # 6/10
    parameters:
      density: 0.3
      weight: 0.1
  - model: Nitral-AI/Poppy_Porpoise-1.0-L3-8B # 7/10
    parameters:
      density: 0.5
      weight: 0.18
  - model: openlynn/Llama-3-Soliloquy-8B-v2 # 8/10
    parameters:
      density: 0.5
      weight: 0.18
  - model: Hastagaras/UltimateANJIR-8B-L3-Blackroot # 6/10
    parameters:
      density: 0.3
      weight: 0.1
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS # 7/10
    parameters:
      density: 0.4
      weight: 0.14
  - model: Sao10K/L3-8B-Stheno-v3.1 # 9/10
    parameters:
      density: 0.6
      weight: 0.23
merge_method: breadcrumbs_ties
base_model: failspy/Llama-3-8B-Instruct-MopeyMule
parameters:
  normalize: false
  rescale: true
  gamma: 0.01
dtype: float16
name: Peter