63 lines
1.2 KiB
Markdown
63 lines
1.2 KiB
Markdown
---
|
|
base_model:
|
|
- jaspionjader/knfp-2-8b
|
|
- jaspionjader/Kosmos-EVAA-Franken-Immersive-v40-8B
|
|
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 SLERP merge method.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* [jaspionjader/knfp-2-8b](https://huggingface.co/jaspionjader/knfp-2-8b)
|
|
* [jaspionjader/Kosmos-EVAA-Franken-Immersive-v40-8B](https://huggingface.co/jaspionjader/Kosmos-EVAA-Franken-Immersive-v40-8B)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
slices:
|
|
- sources:
|
|
- model: jaspionjader/Kosmos-EVAA-Franken-Immersive-v40-8B
|
|
layer_range:
|
|
- 0
|
|
- 32
|
|
- model: jaspionjader/knfp-2-8b
|
|
layer_range:
|
|
- 0
|
|
- 32
|
|
merge_method: slerp
|
|
base_model: jaspionjader/Kosmos-EVAA-Franken-Immersive-v40-8B
|
|
parameters:
|
|
t:
|
|
- filter: self_attn
|
|
value:
|
|
- 0.13
|
|
- 0.19
|
|
- 0.21
|
|
- 0.5
|
|
- 0.12
|
|
- filter: mlp
|
|
value:
|
|
- 0.12
|
|
- 0.21
|
|
- 0.19
|
|
- 0.5
|
|
- 0.13
|
|
- value: 0.17
|
|
dtype: bfloat16
|
|
|
|
```
|