---
base_model:
- SakanaAI/TinySwallow-1.5B-Instruct
- rubenroy/Zurich-1.5B-GCv2-5m
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:
* [SakanaAI/TinySwallow-1.5B-Instruct](https://huggingface.co/SakanaAI/TinySwallow-1.5B-Instruct)
* [rubenroy/Zurich-1.5B-GCv2-5m](https://huggingface.co/rubenroy/Zurich-1.5B-GCv2-5m)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
      - model: SakanaAI/TinySwallow-1.5B-Instruct
        layer_range: [0, 28]
      - model: rubenroy/Zurich-1.5B-GCv2-5m
        layer_range: [0, 28]
merge_method: slerp
base_model: rubenroy/Zurich-1.5B-GCv2-5m
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16
```