SFBAI/multillama-3.2-merge

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using bunnycore/Llama-3.2-3B-RP-DeepThink as a base.

Models Merged

The following models were included in the merge:

• bunnycore/Llama-3.2-3B-Creative
• NousResearch/Hermes-3-Llama-3.2-3B
• Lyte/Llama-3.2-3B-Overthinker
• bunnycore/Llama-3.2-3B-Prodigy
• huihui-ai/Llama-3.2-3B-Instruct-abliterated
• Hastagaras/L3.2-JametMini-3B-MK.I
• bunnycore/Llama-3.2-3B-Pure-RP

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Lyte/Llama-3.2-3B-Overthinker
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Pure-RP
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Prodigy
    parameters:
      density: 0.5
      weight: 0.5
  - model: Hastagaras/L3.2-JametMini-3B-MK.I
    parameters:
      density: 0.5
      weight: 0.5
  - model: NousResearch/Hermes-3-Llama-3.2-3B
    parameters:
      density: 0.5
      weight: 0.5 
  - model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Creative
    parameters:
      density: 0.5
      weight: 0.5
      
merge_method: ties
base_model:  bunnycore/Llama-3.2-3B-RP-DeepThink
parameters:
  normalize: true
  int8_mask: true
dtype: float16