---
base_model:
- Retreatcost/KansenSakura-Radiance-RP-12b
- Vortex5/Lunar-Nexus-12B
- Vortex5/Shadow-Crystal-12B
library_name: transformers
tags:
- mergekit
- merge
- roleplay
---
# Radiant-Shadow-12B

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

📒Notes: I had some issues with chatml instruction template, try Mistral V7 works well.

## Merge Details
### Merge Method

This model was merged using the Passthrough merge method.

### Models Merged

The following models were included in the merge:
* [Retreatcost/KansenSakura-Radiance-RP-12b](https://huggingface.co/Retreatcost/KansenSakura-Radiance-RP-12b)
* [Vortex5/Lunar-Nexus-12B](https://huggingface.co/Vortex5/Lunar-Nexus-12B)
* [Vortex5/Shadow-Crystal-12B](https://huggingface.co/Vortex5/Shadow-Crystal-12B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
- sources:
  - model: Vortex5/Lunar-Nexus-12B
    layer_range: [0, 17]

- sources:
  - model: Retreatcost/KansenSakura-Radiance-RP-12b
    layer_range: [17, 31]

- sources:
  - model: Vortex5/Shadow-Crystal-12B
    layer_range: [31, 40]
merge_method: passthrough
dtype: bfloat16
tokenizer:
  source: union
```