bunnycore/Phi-3.5-mini-dare_ties

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 microsoft/Phi-3.5-mini-instruct + bunnycore/Phi-3.1-EvolKit-lora as a base.

Models Merged

The following models were included in the merge:

• nbeerbower/phi3.5-gutenberg-4B + bunnycore/Phi-3.1-EvolKit-lora
• bunnycore/Phi-3.5-Mini-ChatML + bunnycore/Phi-3.1-EvolKit-lora

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Phi-3.5-Mini-ChatML+bunnycore/Phi-3.1-EvolKit-lora
    parameters:
      density: 0.5
      weight: 1.0
  - model: nbeerbower/phi3.5-gutenberg-4B+bunnycore/Phi-3.1-EvolKit-lora
    parameters:
      density: 0.5
      weight: 1.0

merge_method: dare_ties
base_model: microsoft/Phi-3.5-mini-instruct+bunnycore/Phi-3.1-EvolKit-lora
parameters:
  normalize: false
  int8_mask: true
dtype: float16