AlekseiPravdin's picture
Create README.md
4349410 verified
|
raw
history blame
893 Bytes
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- SanjiWatsuki/Kunoichi-DPO-v2-7B
- AlekseiPravdin/KSI-RP-NSK-128k-7B
---
# Seamaiiza-7B-v1
Seamaiiza-7B-v1 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [AlekseiPravdin/KSI-RP-NSK-128k-7B](https://huggingface.co/AlekseiPravdin/KSI-RP-NSK-128k-7B)
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: AlekseiPravdin/KSI-RP-NSK-128k-7B
layer_range: [0, 32]
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
layer_range: [0, 32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
parameters:
t:
- filter: self_attn
value: [0, 0.53, 0.35, 0.7, 1]
- filter: mlp
value: [1, 0.57, 0.75, 0.33, 0]
- value: 0.53
dtype: bfloat16
```