mergekit-community/mergekit-dare_ties-wqlkund

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using alpindale/Llama-3.2-3B as a base.

Models Merged

The following models were included in the merge:

• belyakoff/llama-3.2-3b-instruct-fine-tuned
• unsloth/Llama-3.2-3B-Instruct
• Medragondot/llama-3.2-3b-thinking

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: alpindale/Llama-3.2-3B
    parameters:
      weight: 0.3
  - model: unsloth/Llama-3.2-3B-Instruct
    parameters:
      density: 0.3
      weight: 0.25
  - model: belyakoff/llama-3.2-3b-instruct-fine-tuned
    parameters:
      density: 0.3
      weight: 0.25
  - model: Medragondot/llama-3.2-3b-thinking
    parameters:
      density: 0.15
      weight: 0.2

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