mergekit-uploader's picture
Upload folder using huggingface_hub
7d8fd07 verified
---
base_model:
- mergekit-community/MN-Hekate-Nykhia-17B
- mergekit-community/MN-Hekate-Episkopos-17B
- mergekit-community/MN-Hekate-Limenoskopos-12B
- mergekit-community/MN-Hekate-Nyktipolos-17B
- mergekit-community/MN-Hekate-Limenoskopos-17B
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mergekit-community/MN-Hekate-Limenoskopos-12B](https://huggingface.co/mergekit-community/MN-Hekate-Limenoskopos-12B) as a base.
### Models Merged
The following models were included in the merge:
* [mergekit-community/MN-Hekate-Nykhia-17B](https://huggingface.co/mergekit-community/MN-Hekate-Nykhia-17B)
* [mergekit-community/MN-Hekate-Episkopos-17B](https://huggingface.co/mergekit-community/MN-Hekate-Episkopos-17B)
* [mergekit-community/MN-Hekate-Nyktipolos-17B](https://huggingface.co/mergekit-community/MN-Hekate-Nyktipolos-17B)
* [mergekit-community/MN-Hekate-Limenoskopos-17B](https://huggingface.co/mergekit-community/MN-Hekate-Limenoskopos-17B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mergekit-community/MN-Hekate-Limenoskopos-12B
slices:
- sources:
- model: mergekit-community/MN-Hekate-Limenoskopos-12B
layer_range: [0, 12]
- sources:
- model: mergekit-community/MN-Hekate-Limenoskopos-12B
layer_range: [12, 16]
- model: mergekit-community/MN-Hekate-Episkopos-17B
layer_range: [12, 16]
- model: mergekit-community/MN-Hekate-Nykhia-17B
layer_range: [12, 16]
- model: mergekit-community/MN-Hekate-Nyktipolos-17B
layer_range: [12, 16]
- model: mergekit-community/MN-Hekate-Limenoskopos-17B
layer_range: [12, 16]
- sources:
- model: mergekit-community/MN-Hekate-Limenoskopos-12B
layer_range: [16, 20]
- model: mergekit-community/MN-Hekate-Episkopos-17B
layer_range: [20, 24]
- model: mergekit-community/MN-Hekate-Nykhia-17B
layer_range: [20, 24]
- model: mergekit-community/MN-Hekate-Nyktipolos-17B
layer_range: [20, 24]
- model: mergekit-community/MN-Hekate-Limenoskopos-17B
layer_range: [20, 24]
- sources:
- model: mergekit-community/MN-Hekate-Limenoskopos-12B
layer_range: [20, 28]
- model: mergekit-community/MN-Hekate-Episkopos-17B
layer_range: [24, 32]
- model: mergekit-community/MN-Hekate-Episkopos-17B
layer_range: [36, 44]
- model: mergekit-community/MN-Hekate-Nykhia-17B
layer_range: [24, 32]
- model: mergekit-community/MN-Hekate-Nykhia-17B
layer_range: [36, 44]
- model: mergekit-community/MN-Hekate-Nyktipolos-17B
layer_range: [24, 32]
- model: mergekit-community/MN-Hekate-Nyktipolos-17B
layer_range: [36, 44]
- model: mergekit-community/MN-Hekate-Limenoskopos-17B
layer_range: [24, 32]
- model: mergekit-community/MN-Hekate-Limenoskopos-17B
layer_range: [36, 44]
- sources:
- model: mergekit-community/MN-Hekate-Limenoskopos-12B
layer_range: [28, 32]
- model: mergekit-community/MN-Hekate-Episkopos-17B
layer_range: [32, 36]
- model: mergekit-community/MN-Hekate-Episkopos-17B
layer_range: [44, 48]
- model: mergekit-community/MN-Hekate-Nykhia-17B
layer_range: [32, 36]
- model: mergekit-community/MN-Hekate-Nykhia-17B
layer_range: [44, 48]
- model: mergekit-community/MN-Hekate-Nyktipolos-17B
layer_range: [32, 36]
- model: mergekit-community/MN-Hekate-Nyktipolos-17B
layer_range: [44, 48]
- model: mergekit-community/MN-Hekate-Limenoskopos-17B
layer_range: [32, 36]
- model: mergekit-community/MN-Hekate-Limenoskopos-17B
layer_range: [44, 48]
- sources:
- model: mergekit-community/MN-Hekate-Limenoskopos-12B
layer_range: [32, 40]
- model: mergekit-community/MN-Hekate-Episkopos-17B
layer_range: [48, 56]
- model: mergekit-community/MN-Hekate-Nykhia-17B
layer_range: [48, 56]
- model: mergekit-community/MN-Hekate-Nyktipolos-17B
layer_range: [48, 56]
- model: mergekit-community/MN-Hekate-Limenoskopos-17B
layer_range: [48, 56]
parameters:
weight: 3
```