39 lines
896 B
Markdown
39 lines
896 B
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
tags:
|
||
|
|
- merge
|
||
|
|
- mergekit
|
||
|
|
---
|
||
|
|
|
||
|
|
# Malachite-7b-v0
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
This model is a merge of the following models made with [mergekit](https://github.com/cg123/mergekit):
|
||
|
|
* [zyh3826/GML-Mistral-merged-v1](https://huggingface.co/zyh3826/GML-Mistral-merged-v1)
|
||
|
|
* [cookinai/CatMacaroni-Slerp](https://huggingface.co/cookinai/CatMacaroni-Slerp)
|
||
|
|
|
||
|
|
## 🧩 Configuration
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- model: zyh3826/GML-Mistral-merged-v1
|
||
|
|
layer_range: [0, 32]
|
||
|
|
- model: cookinai/CatMacaroni-Slerp
|
||
|
|
layer_range: [0, 32]
|
||
|
|
merge_method: slerp
|
||
|
|
base_model: cookinai/CatMacaroni-Slerp
|
||
|
|
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: bfloat16
|
||
|
|
```
|