初始化项目,由ModelHub XC社区提供模型
Model: Kamka-IT/shadow-clown-BioMistral-7B-SLERP Source: Original Platform
This commit is contained in:
36
README.md
Normal file
36
README.md
Normal file
@@ -0,0 +1,36 @@
|
||||
---
|
||||
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
|
||||
\```
|
||||
Reference in New Issue
Block a user