|
--- |
|
base_model: |
|
- Aryanne/Astrea-RP-v1.5-3B |
|
- jeiku/Refined_3B |
|
- Aryanne/Astrea-RP-v1-3B |
|
tags: |
|
- mergekit |
|
- merge |
|
license: other |
|
--- |
|
|
|
Will probably merge it with more models in the future. |
|
|
|
# Merged |
|
|
|
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 passthrough merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [Aryanne/Astrea-RP-v1.5-3B](https://huggingface.co/Aryanne/Astrea-RP-v1.5-3B) |
|
* [jeiku/Refined_3B](https://huggingface.co/jeiku/Refined_3B) |
|
* [Aryanne/Astrea-RP-v1-3B](https://huggingface.co/Aryanne/Astrea-RP-v1-3B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
dtype: bfloat16 |
|
merge_method: passthrough |
|
slices: |
|
- sources: |
|
- layer_range: [0, 10] |
|
model: Aryanne/Astrea-RP-v1.5-3B |
|
- sources: |
|
- layer_range: [10, 14] |
|
model: jeiku/Refined_3B |
|
- sources: |
|
- layer_range: [7, 14] |
|
model: Aryanne/Astrea-RP-v1-3B |
|
- sources: |
|
- layer_range: [13, 19] |
|
model: jeiku/Refined_3B |
|
- sources: |
|
- layer_range: [18, 25] |
|
model: Aryanne/Astrea-RP-v1-3B |
|
- sources: |
|
- layer_range: [18, 22] |
|
model: jeiku/Refined_3B |
|
- sources: |
|
- layer_range: [22, 32] |
|
model: Aryanne/Astrea-RP-v1.5-3B |
|
``` |
|
# License |
|
|
|
I think zephyr license applies to this merge, for non commercial use. |
