49 lines
1.1 KiB
Markdown
49 lines
1.1 KiB
Markdown
|
|
---
|
||
|
|
base_model:
|
||
|
|
- SvalTek/Qwen2.5-ColdBrew
|
||
|
|
- Orion-zhen/Meissa-Qwen2.5-7B-Instruct
|
||
|
|
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [SvalTek/Qwen2.5-ColdBrew](https://huggingface.co/SvalTek/Qwen2.5-ColdBrew) as a base.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* [Orion-zhen/Meissa-Qwen2.5-7B-Instruct](https://huggingface.co/Orion-zhen/Meissa-Qwen2.5-7B-Instruct)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
|
||
|
|
name: MQ-Coldbrew-Base-Test0
|
||
|
|
merge_method: ties
|
||
|
|
base_model: SvalTek/Qwen2.5-ColdBrew
|
||
|
|
models:
|
||
|
|
- model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
|
||
|
|
parameters:
|
||
|
|
weight: 0.6
|
||
|
|
density: 0.7
|
||
|
|
- model: SvalTek/Qwen2.5-ColdBrew
|
||
|
|
parameters:
|
||
|
|
weight: 0.4
|
||
|
|
density: 0.75
|
||
|
|
parameters:
|
||
|
|
normalize: true
|
||
|
|
int8_mask: false
|
||
|
|
dtype: bfloat16
|
||
|
|
|
||
|
|
```
|