metadata
base_model:
- Vortex5/VoidRose-24B
- Gryphe/Pantheon-RP-1.8-24b-Small-3.1
- aixonlab/Eurydice-24b-v3.5
- trashpanda-org/MS-24B-Instruct-Mullein-v0
- Vortex5/WittyAthena-24b
- LatitudeGames/Harbinger-24B
- TheDrummer/Cydonia-24B-v3
library_name: transformers
tags:
- mergekit
- merge
- roleplay
NovaSage-24B
NovaSage-24B is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using Vortex5/WittyAthena-24b as a base.
Models Merged
The following models were included in the merge:
- Vortex5/VoidRose-24B
- Gryphe/Pantheon-RP-1.8-24b-Small-3.1
- aixonlab/Eurydice-24b-v3.5
- trashpanda-org/MS-24B-Instruct-Mullein-v0
- LatitudeGames/Harbinger-24B
- TheDrummer/Cydonia-24B-v3
Configuration
The following YAML configuration was used to produce this model:
base_model: Vortex5/WittyAthena-24b
models:
- model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
- model: trashpanda-org/MS-24B-Instruct-Mullein-v0
- model: Vortex5/VoidRose-24B
- model: TheDrummer/Cydonia-24B-v3
- model: aixonlab/Eurydice-24b-v3.5
- model: LatitudeGames/Harbinger-24B
merge_method: model_stock
dtype: bfloat16
parameters:
normalize: true