---
base_model:
- pansophic/rocket-3B
- jeiku/Rosa_v1_3B
- jondurbin/airoboros-3b-3p0
- cxllin/StableHermes-3b
- stabilityai/stablelm-zephyr-3b
tags:
- mergekit
- merge

---
# Luna7B

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 [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) as a base.

### Models Merged

The following models were included in the merge:
* [pansophic/rocket-3B](https://huggingface.co/pansophic/rocket-3B)
* [jondurbin/airoboros-3b-3p0](https://huggingface.co/jondurbin/airoboros-3b-3p0)
* [cxllin/StableHermes-3b](https://huggingface.co/cxllin/StableHermes-3b)
* [stabilityai/stablelm-zephyr-3b](https://huggingface.co/stabilityai/stablelm-zephyr-3b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: task_arithmetic
base_model: jeiku/Rosa_v1_3B
models:
  - model: jondurbin/airoboros-3b-3p0
    parameters:
      weight: 0.35
  - model: pansophic/rocket-3B
    parameters:
      weight: 0.15
  - model: stabilityai/stablelm-zephyr-3b
    parameters:
      weight: 0.15
  - model: cxllin/StableHermes-3b
    parameters:
      weight: 0.35
dtype: float16
```