---
base_model:
- PowerInfer/SmallThinker-3B-Preview
- Qwen/Qwen2.5-3B-Instruct
- bunnycore/Qwen2.5-3B-RP-Mix
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/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) as a base.

### Models Merged

The following models were included in the merge:
* [PowerInfer/SmallThinker-3B-Preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview)
* [bunnycore/Qwen2.5-3B-RP-Mix](https://huggingface.co/bunnycore/Qwen2.5-3B-RP-Mix)

### Configuration

The following YAML configuration was used to produce this model:

```yaml


merge_method: model_stock
dtype: float16
normalize: true
base_model: Qwen/Qwen2.5-3B-Instruct
models:
  - model: PowerInfer/SmallThinker-3B-Preview
  - model: bunnycore/Qwen2.5-3B-RP-Mix
```