|
|
--- |
|
|
base_model: |
|
|
- mergekit-community/mergekit-passthrough-gujurtn |
|
|
- mergekit-community/mergekit-passthrough-pfwrakj |
|
|
- mergekit-community/mergekit-passthrough-zyecuzy |
|
|
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/mergekit-passthrough-pfwrakj](https://huggingface.co/mergekit-community/mergekit-passthrough-pfwrakj) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [mergekit-community/mergekit-passthrough-gujurtn](https://huggingface.co/mergekit-community/mergekit-passthrough-gujurtn) |
|
|
* [mergekit-community/mergekit-passthrough-zyecuzy](https://huggingface.co/mergekit-community/mergekit-passthrough-zyecuzy) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
dtype: bfloat16 |
|
|
merge_method: model_stock |
|
|
base_model: mergekit-community/mergekit-passthrough-pfwrakj |
|
|
slices: |
|
|
- sources: |
|
|
- model: mergekit-community/mergekit-passthrough-pfwrakj |
|
|
layer_range: [0, 20] |
|
|
- model: mergekit-community/mergekit-passthrough-zyecuzy |
|
|
layer_range: [0, 20] |
|
|
- model: mergekit-community/mergekit-passthrough-gujurtn |
|
|
layer_range: [0, 20] |
|
|
|
|
|
- sources: |
|
|
- model: mergekit-community/mergekit-passthrough-pfwrakj |
|
|
layer_range: [20, 56] |
|
|
|
|
|
- sources: |
|
|
- model: mergekit-community/mergekit-passthrough-pfwrakj |
|
|
layer_range: [56, 76] |
|
|
|
|
|
- model: mergekit-community/mergekit-passthrough-zyecuzy |
|
|
layer_range: [20, 40] |
|
|
|
|
|
- model: mergekit-community/mergekit-passthrough-gujurtn |
|
|
layer_range: [20, 40] |
|
|
``` |
|
|
|