56 lines
1.2 KiB
Markdown
56 lines
1.2 KiB
Markdown
|
---
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen2.5-7B
|
||
|
|
- wvnvwn/qwen-2.5-7B-SSFT-lr3e-5
|
||
|
|
- wvnvwn/qwen-2.5-7B-SSFT-gsm8k-lr3e-5
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
|
||
|
|
---
|
||
|
|
# base_0.5
|
||
|
|
|
||
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||
|
|
|
||
|
|
## Merge Details
|
||
|
|
### Merge Method
|
||
|
|
|
||
|
|
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B)
|
||
|
|
* [wvnvwn/qwen-2.5-7B-SSFT-lr3e-5](https://huggingface.co/wvnvwn/qwen-2.5-7B-SSFT-lr3e-5)
|
||
|
|
* [wvnvwn/qwen-2.5-7B-SSFT-gsm8k-lr3e-5](https://huggingface.co/wvnvwn/qwen-2.5-7B-SSFT-gsm8k-lr3e-5)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
dtype: float16
|
||
|
|
merge_method: linear
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- layer_range: [0, 28]
|
||
|
|
model:
|
||
|
|
model:
|
||
|
|
path: wvnvwn/qwen-2.5-7B-SSFT-gsm8k-lr3e-5
|
||
|
|
parameters:
|
||
|
|
weight: 1.0
|
||
|
|
- layer_range: [0, 28]
|
||
|
|
model:
|
||
|
|
model:
|
||
|
|
path: wvnvwn/qwen-2.5-7B-SSFT-lr3e-5
|
||
|
|
parameters:
|
||
|
|
weight: 0.5
|
||
|
|
- layer_range: [0, 28]
|
||
|
|
model:
|
||
|
|
model:
|
||
|
|
path: Qwen/Qwen2.5-7B
|
||
|
|
parameters:
|
||
|
|
weight: -0.5
|
||
|
|
```
|