56 lines
1.5 KiB
Markdown
56 lines
1.5 KiB
Markdown
---
|
|
base_model:
|
|
- Qwen/Qwen3-1.7B
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# runname_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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* /scratch/final_project/code/group_model/models/Qwen3-1.7B-general
|
|
* /scratch/final_project/code/group_model/models/Qwen3-1.7B-safety
|
|
* /scratch/final_project/code/group_model/models/Qwen3-1.7B-math
|
|
* /scratch/final_project/code/group_model/models/Qwen3-1.7B-multilingual
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
models:
|
|
- model: Qwen/Qwen3-1.7B
|
|
- model: /scratch/final_project/code/group_model/models/Qwen3-1.7B-math
|
|
parameters:
|
|
density: 0.53
|
|
weight: 0.35
|
|
- model: /scratch/final_project/code/group_model/models/Qwen3-1.7B-general
|
|
parameters:
|
|
density: 0.53
|
|
weight: 0.25
|
|
- model: /scratch/final_project/code/group_model/models/Qwen3-1.7B-multilingual
|
|
parameters:
|
|
density: 0.53
|
|
weight: 0.25
|
|
- model: /scratch/final_project/code/group_model/models/Qwen3-1.7B-safety
|
|
parameters:
|
|
density: 0.53
|
|
weight: 0.15
|
|
merge_method: dare_ties
|
|
base_model: Qwen/Qwen3-1.7B
|
|
parameters:
|
|
int8_mask: true
|
|
dtype: bfloat16
|
|
```
|