bunnycore/Llama-3.2-3B-Stock

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 alpindale/Llama-3.2-3B as a base.

Models Merged

The following models were included in the merge:

• KingNish/Reasoning-Llama-3b-v0.1
• chuanli11/Llama-3.2-3B-Instruct-uncensored
• alpindale/Llama-3.2-3B-Instruct
• Hastagaras/L3.2-JametMini-3B-MK.III
• bunnycore/Llama-3.2-3B-TitanFusion-v2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Hastagaras/L3.2-JametMini-3B-MK.III
    parameters:
      weight: 1
      density: 1

  - model: KingNish/Reasoning-Llama-3b-v0.1
    parameters:
      weight: 1
      density: 1


  - model: bunnycore/Llama-3.2-3B-TitanFusion-v2
    parameters:
      weight: 1
      density: 1

  - model: chuanli11/Llama-3.2-3B-Instruct-uncensored
    parameters:
      weight: 1
      density: 1
      
  - model: alpindale/Llama-3.2-3B-Instruct
    parameters:
      weight: 1
      density: 1

merge_method: model_stock
base_model: alpindale/Llama-3.2-3B
parameters:
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16