46 lines
1.4 KiB
Markdown
46 lines
1.4 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
tags:
|
||
|
|
- merge
|
||
|
|
- mergekit
|
||
|
|
- bardsai/jaskier-7b-dpo-v5.6
|
||
|
|
- mlabonne/AlphaMonarch-7B
|
||
|
|
- mlabonne/NeuralMonarch-7B
|
||
|
|
- macadeliccc/MBX-7B-v3-DPO
|
||
|
|
---
|
||
|
|
|
||
|
|
<img src="pastiche-crown-clown.png" alt="Pastiche crown clown logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
||
|
|
|
||
|
|
# pastiche-crown-clown-7B-dare
|
||
|
|
|
||
|
|
pastiche-crown-clown-7B-dare is a DARE merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
||
|
|
* [bardsai/jaskier-7b-dpo-v5.6](https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6)
|
||
|
|
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
|
||
|
|
* [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B)
|
||
|
|
* [macadeliccc/MBX-7B-v3-DPO](https://huggingface.co/macadeliccc/MBX-7B-v3-DPO)
|
||
|
|
|
||
|
|
See the paper [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://arxiv.org/abs/2311.03099) for more on the method.
|
||
|
|
|
||
|
|
## 🧩 Configuration
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
models:
|
||
|
|
- model: bardsai/jaskier-7b-dpo-v5.6
|
||
|
|
- model: mlabonne/AlphaMonarch-7B
|
||
|
|
parameters:
|
||
|
|
density: 0.53
|
||
|
|
weight: 0.2
|
||
|
|
- model: mlabonne/NeuralMonarch-7B
|
||
|
|
parameters:
|
||
|
|
density: 0.53
|
||
|
|
weight: 0.4
|
||
|
|
- model: macadeliccc/MBX-7B-v3-DPO
|
||
|
|
parameters:
|
||
|
|
density: 0.53
|
||
|
|
weight: 0.4
|
||
|
|
merge_method: dare_ties
|
||
|
|
base_model: bardsai/jaskier-7b-dpo-v5.6
|
||
|
|
parameters:
|
||
|
|
int8_mask: true
|
||
|
|
dtype: bfloat16
|
||
|
|
```
|