Modelpublic

ndavidson/phi-3.1-qlora-blend-dpo-abliterated

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes18downloads

Model Card

phi-3.1-qlora-blend-dpo-abliterated

phi-3.1-qlora-blend-dpo-abliterated is a merge of the following models using mergekit:

—ndavidson/phi-3.1-abliterated
—ndavidson/phi-3.1-qlora-blend-dpo

🧩 Configuration

yaml

models:
  - model: microsoft/Phi-3-mini-4k-instruct
    # no parameters necessary for base model
  - model: ndavidson/phi-3.1-abliterated
    parameters:
      density: 0.5
      weight: 0.5
  - model: ndavidson/phi-3.1-qlora-blend-dpo
    parameters:
      density: 0.5
      weight: 0.5
merge_method: ties
base_model: microsoft/Phi-3-mini-4k-instruct
parameters:
  normalize: true
dtype: float16