mergekit-uploader's picture
Upload folder using huggingface_hub
a83e451 verified
---
base_model:
- kainatq/Kaiden-gang-12B
- mergekit-community/Slush-FallMix-Fire_Edition_1.0-12B
- Skarmorie/Aurelias-Garden-12b
- yamatazen/Amelia-SCE-12B
library_name: transformers
tags:
- mergekit
- merge
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [Linear DELLA](https://arxiv.org/abs/2406.11617) merge method using [yamatazen/Amelia-SCE-12B](https://huggingface.co/yamatazen/Amelia-SCE-12B) as a base.
### Models Merged
The following models were included in the merge:
* [kainatq/Kaiden-gang-12B](https://huggingface.co/kainatq/Kaiden-gang-12B)
* [mergekit-community/Slush-FallMix-Fire_Edition_1.0-12B](https://huggingface.co/mergekit-community/Slush-FallMix-Fire_Edition_1.0-12B)
* [Skarmorie/Aurelias-Garden-12b](https://huggingface.co/Skarmorie/Aurelias-Garden-12b)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: yamatazen/Amelia-SCE-12B
parameters:
weight: 0.2
density: 0.5
- model: Skarmorie/Aurelias-Garden-12b
parameters:
weight: 0.2
density: 0.6
- model: kainatq/Kaiden-gang-12B
parameters:
weight: 0.2
density: 0.6
- model: mergekit-community/Slush-FallMix-Fire_Edition_1.0-12B
parameters:
weight: 0.4
density: 0.8
merge_method: della_linear
base_model: yamatazen/Amelia-SCE-12B
parameters:
epsilon: 0.1
lambda: 1
dtype: bfloat16
tokenizer_source: base
```