metadata
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- ndavidson/phi-3.1-qlorablend-1
- ndavidson/phi-3.1-qlorablend-0
phi-3.1-qlora-blend-dpo
phi-3.1-qlora-blend-dpo is a merge of the following models using mergekit:
🧩 Configuration
models:
- model: microsoft/Phi-3-mini-4k-instruct
# no parameters necessary for base model
- model: ndavidson/phi-3.1-qlorablend-1
parameters:
density: 0.5
weight: 0.5
- model: ndavidson/phi-3.1-qlorablend-0
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: microsoft/Phi-3-mini-4k-instruct
parameters:
normalize: true
dtype: float16