| base_model: | |
| - deca-ai/2-pro-medical | |
| - deca-ai/2-pro-legal | |
| - deca-ai/2-pro-base | |
| - deca-ai/2-pro-math | |
| 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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [deca-ai/2-pro-base](https://huggingface.co/deca-ai/2-pro-base) as a base. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [deca-ai/2-pro-medical](https://huggingface.co/deca-ai/2-pro-medical) | |
| * [deca-ai/2-pro-legal](https://huggingface.co/deca-ai/2-pro-legal) | |
| * [deca-ai/2-pro-math](https://huggingface.co/deca-ai/2-pro-math) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| models: | |
| - model: deca-ai/2-pro-base | |
| #no parameters necessary for base model | |
| - model: deca-ai/2-pro-math | |
| parameters: | |
| density: 0.5 | |
| weight: 0.5 | |
| - model: deca-ai/2-pro-medical | |
| parameters: | |
| density: 0.5 | |
| weight: 0.5 | |
| - model: deca-ai/2-pro-legal | |
| parameters: | |
| density: 0.5 | |
| weight: 0.5 | |
| merge_method: dare_ties | |
| base_model: deca-ai/2-pro-base | |
| parameters: | |
| normalize: false | |
| int8_mask: true | |
| dtype: float16 | |
| ``` | |