Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 18
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using mistralai/Mistral-Nemo-Base-2407 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: flammenai/Mahou-1.5-mistral-nemo-12B
parameters:
weight: 1
density: 1
- model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
parameters:
weight: 1
density: 1
- model: flammenai/Flammades-Mistral-Nemo-12B
parameters:
weight: 1
density: 1
- model: nbeerbower/Mistral-Nemo-Prism-12B-v7
parameters:
weight: 1
density: 1
- model: nbeerbower/mistral-nemo-kartoffel-12B
parameters:
weight: 1
density: 1
- model: nbeerbower/mistral-nemo-bophades3-12B
parameters:
weight: 1
density: 1
merge_method: ties
base_model: mistralai/Mistral-Nemo-Base-2407
parameters:
weight: 1
density: 1
normalize: true
int8_mask: true
dtype: bfloat16
tokenizer:
source: nbeerbower/mistral-nemo-kartoffel-12B