53 lines
1.6 KiB
Markdown
53 lines
1.6 KiB
Markdown
---
|
|
base_model:
|
|
- Etherll/Qwen2.5-7B-della-test
|
|
- marcuscedricridia/Hush-Qwen2.5-7B-Preview
|
|
- marcuscedricridia/absolute-o1-7b
|
|
- Qwen/Qwen2.5-7B
|
|
- marcuscedricridia/sbr-o1-7b
|
|
- marcuscedricridia/Hush-Qwen2.5-7B-RP-v1.1-1M
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# merge
|
|
|
|
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* [Etherll/Qwen2.5-7B-della-test](https://huggingface.co/Etherll/Qwen2.5-7B-della-test)
|
|
* [marcuscedricridia/Hush-Qwen2.5-7B-Preview](https://huggingface.co/marcuscedricridia/Hush-Qwen2.5-7B-Preview)
|
|
* [marcuscedricridia/absolute-o1-7b](https://huggingface.co/marcuscedricridia/absolute-o1-7b)
|
|
* [marcuscedricridia/sbr-o1-7b](https://huggingface.co/marcuscedricridia/sbr-o1-7b)
|
|
* [marcuscedricridia/Hush-Qwen2.5-7B-RP-v1.1-1M](https://huggingface.co/marcuscedricridia/Hush-Qwen2.5-7B-RP-v1.1-1M)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
merge_method: model_stock
|
|
base_model: Qwen/Qwen2.5-7B
|
|
models:
|
|
- model: marcuscedricridia/sbr-o1-7b
|
|
- model: marcuscedricridia/absolute-o1-7b
|
|
- model: marcuscedricridia/Hush-Qwen2.5-7B-RP-v1.1-1M
|
|
- model: marcuscedricridia/Hush-Qwen2.5-7B-Preview
|
|
- model: Etherll/Qwen2.5-7B-della-test
|
|
dtype: bfloat16
|
|
tokenizer_source: base
|
|
int8_mask: true
|
|
normalize: true
|
|
name: Hush-Qwen2.5-7B-MST-v1.3
|
|
|
|
```
|