63 lines
1.1 KiB
Markdown
63 lines
1.1 KiB
Markdown
|
---
|
||
|
|
base_model:
|
||
|
|
- jaspionjader/bh-58
|
||
|
|
- suayptalha/Maestro-R1-Llama-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/bh-58](https://huggingface.co/jaspionjader/bh-58)
|
||
|
|
* [suayptalha/Maestro-R1-Llama-8B](https://huggingface.co/suayptalha/Maestro-R1-Llama-8B)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- model: jaspionjader/bh-58
|
||
|
|
layer_range:
|
||
|
|
- 0
|
||
|
|
- 32
|
||
|
|
- model: suayptalha/Maestro-R1-Llama-8B
|
||
|
|
layer_range:
|
||
|
|
- 0
|
||
|
|
- 32
|
||
|
|
merge_method: slerp
|
||
|
|
base_model: jaspionjader/bh-58
|
||
|
|
parameters:
|
||
|
|
t:
|
||
|
|
- filter: self_attn
|
||
|
|
value:
|
||
|
|
- 0.09
|
||
|
|
- 0.05
|
||
|
|
- 0.07
|
||
|
|
- 0.08
|
||
|
|
- 0.06
|
||
|
|
- filter: mlp
|
||
|
|
value:
|
||
|
|
- 0.06
|
||
|
|
- 0.08
|
||
|
|
- 0.07
|
||
|
|
- 0.05
|
||
|
|
- 0.09
|
||
|
|
- value: 0.07
|
||
|
|
dtype: bfloat16
|
||
|
|
|
||
|
|
```
|