NikitosKey/Merge-Math-Coder-7B-v3

1---2base_model:3- Qwen/Qwen2.5-Coder-7B-Instruct4- Qwen/Qwen2.5-7B-Instruct5- Qwen/Qwen2.5-Math-7B-Instruct6library_name: transformers7tags:8- mergekit9- merge10 11---12# merged_model13 14This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).15 16## Merge Details17### Merge Method18 19This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) as a base.20 21### Models Merged22 23The following models were included in the merge:24* [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)25* [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct)26 27### Configuration28 29The following YAML configuration was used to produce this model:30 31```yaml32 33models:34  - model: Qwen/Qwen2.5-Math-7B-Instruct35    parameters:36      density: 0.537      weight: 0.638  - model: Qwen/Qwen2.5-Coder-7B-Instruct39    parameters:40      density: 0.541      weight: 0.442merge_method: dare_ties43base_model: Qwen/Qwen2.5-7B-Instruct44parameters:45  int8_mask: true46dtype: bfloat1647 48```49