---
base_model:
- Lunzima/NQLSG-Qwen2.5-14B-OriginalFusion
- Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8
- Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v5
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:
* [Lunzima/NQLSG-Qwen2.5-14B-OriginalFusion](https://huggingface.co/Lunzima/NQLSG-Qwen2.5-14B-OriginalFusion)
* [Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8](https://huggingface.co/Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8)
* [Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v5](https://huggingface.co/Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v5)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8
merge_method: slerp
tokenizer_source: base
dtype: bfloat16
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.5
slices:
  - sources:
    - model:       Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8
      layer_range: [0, 24]
    - model:       Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v5
      layer_range: [0, 24]
  - sources:
    - model:       Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8
      layer_range: [24, 48]
    - model:       Lunzima/NQLSG-Qwen2.5-14B-OriginalFusion
      layer_range: [24, 48]

```