---
base_model:
- fblgit/TheBeagle-v2beta-32B-MGS
- Qwen/QwQ-32B
- qihoo360/Light-R1-32B
- deepcogito/cogito-v1-preview-qwen-32B
- Skywork/Skywork-OR1-32B-Preview
- YOYO-AI/Qwen2.5-Coder-32B-YOYO
- AXCXEPT/EZO-Qwen2.5-32B-Instruct
- Qwen/Qwen2.5-32B-Instruct
- tanliboy/lambda-qwen2.5-32b-dpo-test
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/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) as a base.

### Models Merged

The following models were included in the merge:
* [fblgit/TheBeagle-v2beta-32B-MGS](https://huggingface.co/fblgit/TheBeagle-v2beta-32B-MGS)
* [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B)
* [qihoo360/Light-R1-32B](https://huggingface.co/qihoo360/Light-R1-32B)
* [deepcogito/cogito-v1-preview-qwen-32B](https://huggingface.co/deepcogito/cogito-v1-preview-qwen-32B)
* [Skywork/Skywork-OR1-32B-Preview](https://huggingface.co/Skywork/Skywork-OR1-32B-Preview)
* [YOYO-AI/Qwen2.5-Coder-32B-YOYO](https://huggingface.co/YOYO-AI/Qwen2.5-Coder-32B-YOYO)
* [AXCXEPT/EZO-Qwen2.5-32B-Instruct](https://huggingface.co/AXCXEPT/EZO-Qwen2.5-32B-Instruct)
* [tanliboy/lambda-qwen2.5-32b-dpo-test](https://huggingface.co/tanliboy/lambda-qwen2.5-32b-dpo-test)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: YOYO-AI/Qwen2.5-Coder-32B-YOYO
  - model: Qwen/QwQ-32B
  - model: Skywork/Skywork-OR1-32B-Preview
  - model: deepcogito/cogito-v1-preview-qwen-32B
  - model: qihoo360/Light-R1-32B
  - model: AXCXEPT/EZO-Qwen2.5-32B-Instruct
  - model: fblgit/TheBeagle-v2beta-32B-MGS
  - model: tanliboy/lambda-qwen2.5-32b-dpo-test
  - model: Qwen/Qwen2.5-32B-Instruct
merge_method: model_stock
base_model: Qwen/Qwen2.5-32B-Instruct
normalize: true
int8_mask: true
tokenizer_source: base
dtype: float16
```