--- base_model: - prithivMLmods/Deepthink-Reasoning-7B - prithivMLmods/Neumind-Math-7B-Instruct - Qwen/Qwen2.5-7B-Instruct - prithivMLmods/QwQ-LCoT-7B-Instruct - prithivMLmods/QwQ-MathOct-7B library_name: transformers tags: - mergekit - merge --- ![omni.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/VodPeXQO9_KS-wg_R8vKW.png) # **Merge Qwen Based** 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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) as a base. ### Models Merged The following models were included in the merge: * [prithivMLmods/Deepthink-Reasoning-7B](https://huggingface.co/prithivMLmods/Deepthink-Reasoning-7B) * [prithivMLmods/Neumind-Math-7B-Instruct](https://huggingface.co/prithivMLmods/Neumind-Math-7B-Instruct) * [prithivMLmods/QwQ-LCoT-7B-Instruct](https://huggingface.co/prithivMLmods/QwQ-LCoT-7B-Instruct) * [prithivMLmods/QwQ-MathOct-7B](https://huggingface.co/prithivMLmods/QwQ-MathOct-7B) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: prithivMLmods/Deepthink-Reasoning-7B - model: prithivMLmods/QwQ-LCoT-7B-Instruct - model: prithivMLmods/QwQ-MathOct-7B - model: prithivMLmods/Neumind-Math-7B-Instruct merge_method: model_stock base_model: Qwen/Qwen2.5-7B-Instruct normalize: true int8_mask: true dtype: bfloat16 ```