metadata
base_model:
- ibm/merlinite-7b
- mistralai/Mistral-7B-v0.1
- l3utterfly/mistral-7b-v0.1-layla-v4
- SanjiWatsuki/Sonya-7B
- NeverSleep/Noromaid-7b-v0.2
- migtissera/SynthIA-7B-v1.3
library_name: transformers
tags:
- mergekit
- merge
Franken-MistressMaid-7B
This is a merge of pre-trained language models created using mergekit.
Merge Details
See Below
Merge Method
This model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.
Models Merged
The following models were included in the merge:
- ibm/merlinite-7b
- l3utterfly/mistral-7b-v0.1-layla-v4
- SanjiWatsuki/Sonya-7B
- NeverSleep/Noromaid-7b-v0.2
- migtissera/SynthIA-7B-v1.3
Configuration
The following YAML configuration was used to produce this model:
models:
- model: migtissera/SynthIA-7B-v1.3
parameters:
weight: 1
density: 1
- model: ibm/merlinite-7b
parameters:
weight: 0.3
- model: SanjiWatsuki/Sonya-7B
parameters:
weight: 0.2
- model: NeverSleep/Noromaid-7b-v0.2
parameters:
weight: 0.2
- model: l3utterfly/mistral-7b-v0.1-layla-v4
parameters:
weight: 0.2
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
density: 0.4
int8_mask: true
normalize: true
dtype: bfloat16