---
base_model:
- nbeerbower/llama-3-SNAMD-8B
- flammenai/Mahou-1.3a-llama3-8B
- cognitivecomputations/dolphin-2.9.1-llama-3-8b
- flammenai/Mahou-1.2a-llama3-8B
library_name: transformers
tags:
- mergekit
- merge

---
# llama-3-MagicDolphin-8B

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

### Models Merged

The following models were included in the merge:
* [flammenai/Mahou-1.3a-llama3-8B](https://huggingface.co/flammenai/Mahou-1.3a-llama3-8B)
* [cognitivecomputations/dolphin-2.9.1-llama-3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-8b)
* [flammenai/Mahou-1.2a-llama3-8B](https://huggingface.co/flammenai/Mahou-1.2a-llama3-8B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
    - model: flammenai/Mahou-1.2a-llama3-8B
    - model: flammenai/Mahou-1.3a-llama3-8B
    - model: cognitivecomputations/dolphin-2.9.1-llama-3-8b
merge_method: model_stock
base_model: nbeerbower/llama-3-SNAMD-8B
dtype: bfloat16


```