---
base_model:
- bunnycore/Qwen2.5-3B-Model-Stock-v3.1
- bunnycore/QwQen-3B-LCoT
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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.

### Models Merged

The following models were included in the merge:
* [bunnycore/Qwen2.5-3B-Model-Stock-v3.1](https://huggingface.co/bunnycore/Qwen2.5-3B-Model-Stock-v3.1)
* [bunnycore/QwQen-3B-LCoT](https://huggingface.co/bunnycore/QwQen-3B-LCoT)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
- sources:
  - model: bunnycore/QwQen-3B-LCoT
    layer_range:
    - 0
    - 24
  - model: bunnycore/Qwen2.5-3B-Model-Stock-v3.1
    layer_range:
    - 0
    - 24
merge_method: slerp
base_model: bunnycore/QwQen-3B-LCoT
parameters:
  t:
  - filter: self_attn
    value: 0.5
  - filter: mlp
    value: 0.5
  - value: 0.5
dtype: bfloat16
allow_different_architectures: true
skip_module_check: true
```