realYinkaIyiola/Deepseek-R1-Distill-14B-Math-Code-Merged

1---2base_model:3- realYinkaIyiola/Deepseek-R1-Distill-14B-Code4- realYinkaIyiola/Deepseek-R1-Distill-14B-Math5- Qwen/Qwen2.5-14B6library_name: transformers7tags:8- mergekit9- merge10 11---12# FuseO1-DeepSeekR1-Math-Code13 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 sce merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.20 21### Models Merged22 23The following models were included in the merge:24* [realYinkaIyiola/Deepseek-R1-Distill-14B-Code](https://huggingface.co/realYinkaIyiola/Deepseek-R1-Distill-14B-Code)25* [realYinkaIyiola/Deepseek-R1-Distill-14B-Math](https://huggingface.co/realYinkaIyiola/Deepseek-R1-Distill-14B-Math)26 27### Configuration28 29The following YAML configuration was used to produce this model:30 31```yaml32models:33  # Pivot model34  - model: Qwen/Qwen2.5-14B35  # Target models36  - model: realYinkaIyiola/Deepseek-R1-Distill-14B-Math37  - model: realYinkaIyiola/Deepseek-R1-Distill-14B-Code38merge_method: sce39base_model: Qwen/Qwen2.5-14B40parameters:41  select_topk: 1.042dtype: bfloat1643 44```45