|
|
--- |
|
|
base_model: |
|
|
- mergekit-community/MN-Sappho-g3-12B |
|
|
- Khetterman/DarkAtom-12B-v3 |
|
|
- mergekit-community/MN-Nyx-Chthonia-12B |
|
|
- Khetterman/AbominationScience-12B-v4 |
|
|
- mergekit-community/MN-Hekate-Enodia-12B |
|
|
- Lambent/Gilded-Arsenic-12B |
|
|
- yamatazen/NightWind-12B |
|
|
- mergekit-community/MN-Hekate-Kleidoukhos-12B |
|
|
- mergekit-community/MN-Sappho-j-12B |
|
|
- yamatazen/EtherealAurora-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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Lambent/Gilded-Arsenic-12B](https://huggingface.co/Lambent/Gilded-Arsenic-12B) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [mergekit-community/MN-Sappho-g3-12B](https://huggingface.co/mergekit-community/MN-Sappho-g3-12B) |
|
|
* [Khetterman/DarkAtom-12B-v3](https://huggingface.co/Khetterman/DarkAtom-12B-v3) |
|
|
* [mergekit-community/MN-Nyx-Chthonia-12B](https://huggingface.co/mergekit-community/MN-Nyx-Chthonia-12B) |
|
|
* [Khetterman/AbominationScience-12B-v4](https://huggingface.co/Khetterman/AbominationScience-12B-v4) |
|
|
* [mergekit-community/MN-Hekate-Enodia-12B](https://huggingface.co/mergekit-community/MN-Hekate-Enodia-12B) |
|
|
* [yamatazen/NightWind-12B](https://huggingface.co/yamatazen/NightWind-12B) |
|
|
* [mergekit-community/MN-Hekate-Kleidoukhos-12B](https://huggingface.co/mergekit-community/MN-Hekate-Kleidoukhos-12B) |
|
|
* [mergekit-community/MN-Sappho-j-12B](https://huggingface.co/mergekit-community/MN-Sappho-j-12B) |
|
|
* [yamatazen/EtherealAurora-12B](https://huggingface.co/yamatazen/EtherealAurora-12B) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
dtype: float32 |
|
|
out_dtype: bfloat16 |
|
|
merge_method: model_stock |
|
|
base_model: Lambent/Gilded-Arsenic-12B |
|
|
models: |
|
|
- model: Khetterman/AbominationScience-12B-v4 |
|
|
- model: Khetterman/DarkAtom-12B-v3 |
|
|
- model: mergekit-community/MN-Sappho-g3-12B |
|
|
- model: mergekit-community/MN-Sappho-j-12B |
|
|
- model: mergekit-community/MN-Hekate-Enodia-12B |
|
|
- model: mergekit-community/MN-Hekate-Kleidoukhos-12B |
|
|
- model: mergekit-community/MN-Nyx-Chthonia-12B |
|
|
- model: yamatazen/EtherealAurora-12B |
|
|
- model: yamatazen/NightWind-12B |
|
|
|
|
|
chat_template: chatml |
|
|
tokenizer: |
|
|
source: union |
|
|
tokens: |
|
|
"[INST]": |
|
|
source: mergekit-community/MN-Hekate-Enodia-12B |
|
|
force: true |
|
|
"[/INST]": |
|
|
source: mergekit-community/MN-Hekate-Enodia-12B |
|
|
force: true |
|
|
"<|im_start|>": |
|
|
source: mergekit-community/MN-Hekate-Enodia-12B |
|
|
force: true |
|
|
"<|im_end|>": |
|
|
source: mergekit-community/MN-Hekate-Enodia-12B |
|
|
force: true |
|
|
|
|
|
``` |
|
|
|
