36 lines
920 B
Markdown
36 lines
920 B
Markdown
---
|
|
license: apache-2.0
|
|
tags:
|
|
- merge
|
|
- mergekit
|
|
- lazymergekit
|
|
- CorticalStack/shadow-clown-7B-dare
|
|
- BioMistral/BioMistral-7B-DARE
|
|
---
|
|
|
|
# shadow-clown-BioMistral-7B-SLERP
|
|
|
|
shadow-clown-BioMistral-7B-SLERP is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
|
* [CorticalStack/shadow-clown-7B-dare](https://huggingface.co/CorticalStack/shadow-clown-7B-dare)
|
|
* [BioMistral/BioMistral-7B-DARE](https://huggingface.co/BioMistral/BioMistral-7B-DARE)
|
|
|
|
## 🧩 Configuration
|
|
|
|
\```yaml
|
|
slices:
|
|
- sources:
|
|
- model: CorticalStack/shadow-clown-7B-dare
|
|
layer_range: [0, 32]
|
|
- model: BioMistral/BioMistral-7B-DARE
|
|
layer_range: [0, 32]
|
|
merge_method: slerp
|
|
base_model: CorticalStack/shadow-clown-7B-dare
|
|
parameters:
|
|
t:
|
|
- filter: self_attn
|
|
value: [0, 0.5, 0.3, 0.7, 1]
|
|
- filter: mlp
|
|
value: [1, 0.5, 0.7, 0.3, 0]
|
|
- value: 0.5
|
|
dtype: float16
|
|
\``` |