Resolving Interference When Merging Models
Paper
•
2306.01708
•
Published
•
15
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using ClaudioItaly/1800-9B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: ifable/gemma-2-Ifable-9B
parameters:
density: 0.4
weight: 0.3
- model: sam-paech/Delirium-v1
parameters:
density: 0.8
weight: 0.7
merge_method: ties
base_model: ClaudioItaly/1800-9B
parameters:
normalize: true # Normalizza i pesi
int8_mask: true
dtype: float16