Jebadiah/Tess-gradient-ruby

1---2base_model:3- gradientai/Llama-3-8B-Instruct-Gradient-4194k4- migtissera/Tess-2.0-Llama-3-8B5library_name: transformers6tags:7- mergekit8- merge9 10---11# merge12 13This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).14 15## Merge Details16### Merge Method17 18This model was merged using the linear [DARE](https://arxiv.org/abs/2311.03099) merge method using [migtissera/Tess-2.0-Llama-3-8B](https://huggingface.co/migtissera/Tess-2.0-Llama-3-8B) as a base.19 20### Models Merged21 22The following models were included in the merge:23* [gradientai/Llama-3-8B-Instruct-Gradient-4194k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-4194k)24 25### Configuration26 27The following YAML configuration was used to produce this model:28 29```yaml30models:31  - model: migtissera/Tess-2.0-Llama-3-8B32    # No parameters necessary for base model33  - model: gradientai/Llama-3-8B-Instruct-Gradient-4194k34    parameters:35      density: 0.536      weight: 0.537merge_method: dare_linear38base_model: migtissera/Tess-2.0-Llama-3-8B39parameters:40  int8_mask: true41dtype: bfloat1642```43