---
base_model:
- mlabonne/ChimeraLlama-3-8B
- abacusai/Llama-3-Smaug-8B
- vicgalle/Unsafe-Llama-3-8B
- nbeerbower/llama-3-aura-bophades-8B
- mlabonne/OrpoLlama-3-8B
- cloudyu/Meta-Llama-3-8B-Instruct-DPO
library_name: transformers
license: other
license_name: llama3
tags:
- mergekit
- merge

---
# llama-3-dragon-bophades-8B

This model is based on Llama-3-8b, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE)

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 [nbeerbower/llama-3-aura-bophades-8B](https://huggingface.co/nbeerbower/llama-3-aura-bophades-8B) as a base.

### Models Merged

The following models were included in the merge:
* [mlabonne/ChimeraLlama-3-8B](https://huggingface.co/mlabonne/ChimeraLlama-3-8B)
* [abacusai/Llama-3-Smaug-8B](https://huggingface.co/abacusai/Llama-3-Smaug-8B)
* [vicgalle/Unsafe-Llama-3-8B](https://huggingface.co/vicgalle/Unsafe-Llama-3-8B)
* [mlabonne/OrpoLlama-3-8B](https://huggingface.co/mlabonne/OrpoLlama-3-8B)
* [cloudyu/Meta-Llama-3-8B-Instruct-DPO](https://huggingface.co/cloudyu/Meta-Llama-3-8B-Instruct-DPO)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
    - model: mlabonne/OrpoLlama-3-8B
    - model: mlabonne/ChimeraLlama-3-8B
    - model: abacusai/Llama-3-Smaug-8B
    - model: cloudyu/Meta-Llama-3-8B-Instruct-DPO
    - model: vicgalle/Unsafe-Llama-3-8B
merge_method: model_stock
base_model: nbeerbower/llama-3-aura-bophades-8B
dtype: bfloat16

```