---
base_model:
- huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated
- allenai/Llama-3.1-Tulu-3.1-8B
- meditsolutions/Llama-3.1-MedIT-SUN-8B
library_name: transformers
tags:
- mergekit
- merge

---
# 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 [huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated](https://huggingface.co/huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated) as a base.

### Models Merged

The following models were included in the merge:
* [allenai/Llama-3.1-Tulu-3.1-8B](https://huggingface.co/allenai/Llama-3.1-Tulu-3.1-8B)
* [meditsolutions/Llama-3.1-MedIT-SUN-8B](https://huggingface.co/meditsolutions/Llama-3.1-MedIT-SUN-8B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: model_stock
models:
  - model: meditsolutions/Llama-3.1-MedIT-SUN-8B
    parameters:
      weight: 1.0
  - model: allenai/Llama-3.1-Tulu-3.1-8B
    parameters:
      weight: 1.0
base_model: huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated
dtype: bfloat16
normalize: true
```