Resolving Interference When Merging Models
Paper
β’
2306.01708
β’
Published
β’
15
hello
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using sometimesanotion/Qwenvergence-14B-v11 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: sometimesanotion/Lamarck-14B-v0.7
parameters:
weight: 1
density: 1
merge_method: ties
base_model: sometimesanotion/Qwenvergence-14B-v11
parameters:
weight: 1
density: 1
normalize: true
int8_mask: true
dtype: float16