| base_model: | |
| - rityak/Magnum-DareLinearAbliterated-Instruct-DPO | |
| - rityak/Vikhr-Nemo-dostoevsky-saiga-12b | |
| 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 linear [DARE](https://arxiv.org/abs/2311.03099) merge method using [rityak/Magnum-DareLinearAbliterated-Instruct-DPO](https://huggingface.co/rityak/Magnum-DareLinearAbliterated-Instruct-DPO) as a base. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [rityak/Vikhr-Nemo-dostoevsky-saiga-12b](https://huggingface.co/rityak/Vikhr-Nemo-dostoevsky-saiga-12b) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| models: | |
| - model: rityak/Vikhr-Nemo-dostoevsky-saiga-12b | |
| parameters: | |
| weight: 1.1 | |
| base_model: rityak/Magnum-DareLinearAbliterated-Instruct-DPO | |
| parameters: | |
| normalize: false | |
| int8_mask: true | |
| merge_method: dare_linear | |
| dtype: float32 | |
| out_dtype: bfloat16 | |
| tokenizer_source: base | |
| ``` | |