| base_model: | |
| - ehristoforu/coolqwen-3b-it | |
| - tensopolis/qwen2.5-3b-or1-tensopolis | |
| - bunnycore/QwQen-3B-LCoT | |
| - bunnycore/Qwen2.5-3B-Model-Stock-v2 | |
| 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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [ehristoforu/coolqwen-3b-it](https://huggingface.co/ehristoforu/coolqwen-3b-it) as a base. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [tensopolis/qwen2.5-3b-or1-tensopolis](https://huggingface.co/tensopolis/qwen2.5-3b-or1-tensopolis) | |
| * [bunnycore/QwQen-3B-LCoT](https://huggingface.co/bunnycore/QwQen-3B-LCoT) | |
| * [bunnycore/Qwen2.5-3B-Model-Stock-v2](https://huggingface.co/bunnycore/Qwen2.5-3B-Model-Stock-v2) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| models: | |
| # Pivot model | |
| - model: ehristoforu/coolqwen-3b-it | |
| # Target models | |
| - model: bunnycore/QwQen-3B-LCoT | |
| - model: tensopolis/qwen2.5-3b-or1-tensopolis | |
| - model: bunnycore/Qwen2.5-3B-Model-Stock-v2 | |
| merge_method: sce | |
| base_model: ehristoforu/coolqwen-3b-it | |
| parameters: | |
| select_topk: 1.5 | |
| dtype: bfloat16 | |
| ``` | |