49 lines
1.3 KiB
Markdown
49 lines
1.3 KiB
Markdown
|
---
|
||
|
|
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
|
||
|
|
- chatml
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- ja
|
||
|
|
license: apache-2.0
|
||
|
|
---
|
||
|
|
|
||
|
|
This is a ChatML model.
|
||
|
|
# 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
|
||
|
|
```
|