---
base_model:
- Nexesenex/Llama_3.2_3b_RedKermes_0.30
- cognitivecomputations/Dolphin3.0-Llama3.2-3B
- Nexesenex/mrcuddle_Dark-Hermes3-Llama3.2-3B
library_name: transformers
tags:
- mergekit
- merge
license: llama3.2
---
# about

Creative version of Kermes.

# 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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Nexesenex/Llama_3.2_3b_RedKermes_0.30](https://huggingface.co/Nexesenex/Llama_3.2_3b_RedKermes_0.30) as a base.

### Models Merged

The following models were included in the merge:
* [cognitivecomputations/Dolphin3.0-Llama3.2-3B](https://huggingface.co/cognitivecomputations/Dolphin3.0-Llama3.2-3B)
* [Nexesenex/mrcuddle_Dark-Hermes3-Llama3.2-3B](https://huggingface.co/Nexesenex/mrcuddle_Dark-Hermes3-Llama3.2-3B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: model_stock
models:
  - model: Nexesenex/mrcuddle_Dark-Hermes3-Llama3.2-3B
    parameters:
      weight: 1.0
  - model: cognitivecomputations/Dolphin3.0-Llama3.2-3B
    parameters:
      weight: 1.0
base_model: Nexesenex/Llama_3.2_3b_RedKermes_0.30
dtype: bfloat16
normalize: true
```