README.md

---
base_model:
- ertghiu256/qwen3-multi-reasoner
- ertghiu256/deepseek-r1-0528-distilled-qwen3
library_name: transformers
tags:
- mergekit
- merge

---
# Qwen 3 4b reasoning combination with deepseek

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 [Arcee Fusion](https://arcee.ai) merge method using [ertghiu256/deepseek-r1-0528-distilled-qwen3](https://huggingface.co/ertghiu256/deepseek-r1-0528-distilled-qwen3) as a base.

### Models Merged

The following models were included in the merge:
* [ertghiu256/qwen3-multi-reasoner](https://huggingface.co/ertghiu256/qwen3-multi-reasoner)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: ertghiu256/deepseek-r1-0528-distilled-qwen3
dtype: float16
merge_method: arcee_fusion
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 36]
        model: ertghiu256/deepseek-r1-0528-distilled-qwen3
      - layer_range: [0, 36]
        model: ertghiu256/qwen3-multi-reasoner
```