--- base_model: - bunnycore/Qwen2.5-7B-MixStock-V0.1 - bunnycore/Qwen2.5-7B-RRP-1M - nvidia/AceInstruct-7B - open-r1/OpenR1-Qwen-7B - open-thoughts/OpenThinker-7B 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 [bunnycore/Qwen2.5-7B-RRP-1M](https://huggingface.co/bunnycore/Qwen2.5-7B-RRP-1M) as a base. ### Models Merged The following models were included in the merge: * [bunnycore/Qwen2.5-7B-MixStock-V0.1](https://huggingface.co/bunnycore/Qwen2.5-7B-MixStock-V0.1) * [nvidia/AceInstruct-7B](https://huggingface.co/nvidia/AceInstruct-7B) * [open-r1/OpenR1-Qwen-7B](https://huggingface.co/open-r1/OpenR1-Qwen-7B) * [open-thoughts/OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: # Pivot model - model: bunnycore/Qwen2.5-7B-RRP-1M # Target models - model: open-thoughts/OpenThinker-7B - model: open-r1/OpenR1-Qwen-7B - model: bunnycore/Qwen2.5-7B-MixStock-V0.1 - model: nvidia/AceInstruct-7B merge_method: sce base_model: bunnycore/Qwen2.5-7B-RRP-1M parameters: select_topk: 0.65 int8_mask: true dtype: bfloat16 ```