Resolving Interference When Merging Models
Paper
•
2306.01708
•
Published
•
15
This project utilizes HODACHI/Borea-Phi-3.5-mini-Instruct-Common, a model based on Phi-3.5-mini-Instruct and fine-tuned by Axcxept co., ltd.
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using microsoft/phi-3.5-mini-instruct as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common
parameters:
weight: 1
density: 1
merge_method: ties
base_model: microsoft/phi-3.5-mini-instruct
parameters:
weight: 1
density: 1
normalize: true
int8_mask: true
dtype: float16
Base model
AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common