Nexesenex/Llama_3.2_3b_SmartiCoatz_0.1b_bf16

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated as a base.

Models Merged

The following models were included in the merge:

• MaziyarPanahi/calme-3.3-llamaloi-3b
• prithivMLmods/Llama-Thinker-3B-Preview2
• ValiantLabs/Llama3.2-3B-ShiningValiant2

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
models:
  - model: ValiantLabs/Llama3.2-3B-ShiningValiant2
    parameters:
      weight: 1.0
  - model: prithivMLmods/Llama-Thinker-3B-Preview2
    parameters:
      weight: 1.0
  - model: MaziyarPanahi/calme-3.3-llamaloi-3b
    parameters:
      weight: 1.0
base_model: Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated
dtype: float16
normalize: true