Model Stock: All we need is just a few fine-tuned models
Paper
•
2403.19522
•
Published
•
13
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using mistralai/Mistral-Nemo-Instruct-2407 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: mistralai/Mistral-Nemo-Instruct-2407
models:
- model: LatitudeGames/Muse-12B
- model: anthracite-org/magnum-v4-12b
- model: yamatazen/NeonMaid-12B-v2
- model: SicariusSicariiStuff/Impish_Nemo_12B
- model: crestf411/MN-Slush
- model: Epiculous/Violet_Twilight-v0.2
- model: LatitudeGames/Wayfarer-12B
- model: inflatebot/MN-12B-Mag-Mell-R1
- model: nothingiisreal/MN-12B-Celeste-V1.9
- model: Nitral-AI/Captain-Eris_Violet-V0.420-12B
- model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
merge_method: model_stock
dtype: bfloat16
parameters:
normalize: true
tokenizer:
source: union