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 nbeerbower/Gemma2-Gutenberg-Doppel-9B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: tannedbum/Ellaria-9B
- model: sam-paech/Delirium-v1
- model: inflatebot/G2-9B-Blackout-R1
- model: Delta-Vector/Odin-9B
- model: TheDrummer/Tiger-Gemma-9B-v3
merge_method: model_stock
base_model: nbeerbower/Gemma2-Gutenberg-Doppel-9B
normalize: false
int8_mask: true
dtype: bfloat16