---
base_model:
- Retreatcost/KansenSakura-Erosion-RP-12b
- mistralai/Mistral-Nemo-Instruct-2407
- Retreatcost/KansenSakura-Eclipse-RP-12b
- Retreatcost/KansenSakura-Radiance-RP-12b
library_name: transformers
tags:
- mergekit
- merge
- roleplay
---
# Noir-Blossom-12B

![meadow2](/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F6669a3a617b838fda45637b8%2Fj7TwtpMBdIT-sEEV99dX_.png)

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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) as a base.

### Models Merged

The following models were included in the merge:
* [Retreatcost/KansenSakura-Erosion-RP-12b](https://huggingface.co/Retreatcost/KansenSakura-Erosion-RP-12b)
* [Retreatcost/KansenSakura-Eclipse-RP-12b](https://huggingface.co/Retreatcost/KansenSakura-Eclipse-RP-12b)
* [Retreatcost/KansenSakura-Radiance-RP-12b](https://huggingface.co/Retreatcost/KansenSakura-Radiance-RP-12b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

models:
  - model: Retreatcost/KansenSakura-Erosion-RP-12b
  - model: Retreatcost/KansenSakura-Eclipse-RP-12b
  - model: Retreatcost/KansenSakura-Radiance-RP-12b
merge_method: sce
dtype: bfloat16
base_model: mistralai/Mistral-Nemo-Instruct-2407
parameters:
  select_topk: 0.2
tokenizer:
  source: union

```