--- base_model: - mergekit-community/mergekit-slerp-lupllmg - mergekit-community/mergekit-slerp-rayqjvs - mergekit-community/mergekit-della_linear-byjvyzy 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 DELLA](https://arxiv.org/abs/2406.11617) merge method using [mergekit-community/mergekit-slerp-lupllmg](https://huggingface.co/mergekit-community/mergekit-slerp-lupllmg) as a base. ### Models Merged The following models were included in the merge: * [mergekit-community/mergekit-slerp-rayqjvs](https://huggingface.co/mergekit-community/mergekit-slerp-rayqjvs) * [mergekit-community/mergekit-della_linear-byjvyzy](https://huggingface.co/mergekit-community/mergekit-della_linear-byjvyzy) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: mergekit-community/mergekit-slerp-lupllmg parameters: weight: 0.4 density: 0.8 - model: mergekit-community/mergekit-slerp-rayqjvs parameters: weight: 0.4 density: 0.8 - model: mergekit-community/mergekit-della_linear-byjvyzy parameters: weight: 0.2 density: 0.2 merge_method: della_linear base_model: mergekit-community/mergekit-slerp-lupllmg parameters: epsilon: 0.05 lambda: 1 dtype: bfloat16 tokenizer_source: base ```