Hjgugugjhuhjggg/mergekit-ties-poovzrh

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 huihui-ai/Llama-3.2-3B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• bunnycore/Llama-3.2-3B-TitanFusion
• roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA
• bunnycore/Llama-3.2-3B-Stock
• bunnycore/Llama-3.2-3B-Sci-Think
• noaebbot/llama3.2-3B-insights
• bunnycore/Llama-3.2-3B-Prodigy
• bunnycore/Llama-3.2-3B-TitanFusion-v2
• bunnycore/Llama-3.2-3B-Mix

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Llama-3.2-3B-Prodigy
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Sci-Think
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Stock
    parameters:
      density: 0.5
      weight: 0.5
  - model: roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA
    parameters:
      density: 0.5
      weight: 0.5
  - model: noaebbot/llama3.2-3B-insights
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-TitanFusion-v2
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-TitanFusion
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Mix
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
parameters:
  normalize: false
  int8_mask: true
dtype: float16