base_model: | |
- yamatazen/Ayla-Light-12B-Stock | |
- yamatazen/Aurora-SCE-12B | |
- yamatazen/EtherealLight-12B | |
- yamatazen/Aurora-SCE-12B-v2 | |
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 [yamatazen/Aurora-SCE-12B](https://huggingface.co/yamatazen/Aurora-SCE-12B) as a base. | |
### Models Merged | |
The following models were included in the merge: | |
* [yamatazen/Ayla-Light-12B-Stock](https://huggingface.co/yamatazen/Ayla-Light-12B-Stock) | |
* [yamatazen/EtherealLight-12B](https://huggingface.co/yamatazen/EtherealLight-12B) | |
* [yamatazen/Aurora-SCE-12B-v2](https://huggingface.co/yamatazen/Aurora-SCE-12B-v2) | |
### Configuration | |
The following YAML configuration was used to produce this model: | |
```yaml | |
base_model: yamatazen/Aurora-SCE-12B | |
models: | |
- model: yamatazen/Aurora-SCE-12B-v2 | |
- model: yamatazen/Ayla-Light-12B-Stock | |
- model: yamatazen/EtherealLight-12B | |
merge_method: model_stock | |
dtype: bfloat16 | |
parameters: | |
normalize: true | |
``` | |