92 lines
2.3 KiB
Markdown
92 lines
2.3 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
tags:
|
||
|
|
- merge
|
||
|
|
- mergekit
|
||
|
|
- Gille/StrangeMerges_32-7B-slerp
|
||
|
|
- yam-peleg/Experiment26-7B
|
||
|
|
---
|
||
|
|
|
||
|
|
<img src="shadow_clown.png" alt="Shadow clown logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
||
|
|
|
||
|
|
# shadow-clown-7B-slerp
|
||
|
|
|
||
|
|
shadow-clown-7B-slerp is a DARE merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
||
|
|
* [Gille/StrangeMerges_32-7B-slerp](https://huggingface.co/Gille/StrangeMerges_32-7B-slerp)
|
||
|
|
* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
|
||
|
|
|
||
|
|
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
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
|
||
|
|
layer_range: [0, 32]
|
||
|
|
- model: MSL7/INEX12-7b
|
||
|
|
layer_range: [0, 32]
|
||
|
|
merge_method: slerp
|
||
|
|
base_model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
|
||
|
|
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
|
||
|
|
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- model: liminerity/M7-7b
|
||
|
|
layer_range: [0, 32]
|
||
|
|
- model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
|
||
|
|
layer_range: [0, 32]
|
||
|
|
merge_method: slerp
|
||
|
|
base_model: liminerity/M7-7b
|
||
|
|
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
|
||
|
|
|
||
|
|
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- model: ammarali32/multi_verse_model
|
||
|
|
layer_range: [0, 32]
|
||
|
|
- model: liminerity/merge
|
||
|
|
layer_range: [0, 32]
|
||
|
|
merge_method: slerp
|
||
|
|
base_model: ammarali32/multi_verse_model
|
||
|
|
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
|
||
|
|
|
||
|
|
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- model: Gille/StrangeMerges_32-7B-slerp
|
||
|
|
layer_range: [0, 32]
|
||
|
|
- model: yam-peleg/Experiment26-7B
|
||
|
|
layer_range: [0, 32]
|
||
|
|
merge_method: slerp
|
||
|
|
base_model: Gille/StrangeMerges_32-7B-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
|
||
|
|
```
|