win10/phi-3.5-sakura-yuzu-v3.0

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 win10/Phi-3.5-mini-instruct-24-9-29 as a base.

Models Merged

The following models were included in the merge:

• MaziyarPanahi/calme-2.1-phi3.5-4b + bunnycore/Phi-3.1-EvolKit-lora
• AXCXEPT/Borea-Phi-3.5-mini-Instruct-Coding + bunnycore/Phi-3.1-EvolKit-lora
• ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1 + bunnycore/Phi-3.5-mini-System-lora
• FreedomIntelligence/Apollo2-3.8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1+bunnycore/Phi-3.5-mini-System-lora
    parameters:
      density: 0.5
      weight: 0.5
  - model: FreedomIntelligence/Apollo2-3.8B
    parameters:
      density: 0.5
      weight: 0.5
  - model: AXCXEPT/Borea-Phi-3.5-mini-Instruct-Coding+bunnycore/Phi-3.1-EvolKit-lora
    parameters:
      density: 0.5
      weight: 0.5
  - model: MaziyarPanahi/calme-2.1-phi3.5-4b+bunnycore/Phi-3.1-EvolKit-lora
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: win10/Phi-3.5-mini-instruct-24-9-29
parameters:
  normalize: false
  int8_mask: true
dtype: float16