--- base_model: - YOYO-AI/QwQ-coder-32B - YOYO-AI/QwQ-openhands-coder-32B - Qwen/QwQ-32B - Qwen/Qwen2.5-Coder-32B - YOYO-AI/QwQ-Olympic-coder-32B 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 [Qwen/Qwen2.5-Coder-32B](https://huggingface.co/Qwen/Qwen2.5-Coder-32B) as a base. ### Models Merged The following models were included in the merge: * [YOYO-AI/QwQ-coder-32B](https://huggingface.co/YOYO-AI/QwQ-coder-32B) * [YOYO-AI/QwQ-openhands-coder-32B](https://huggingface.co/YOYO-AI/QwQ-openhands-coder-32B) * [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) * [YOYO-AI/QwQ-Olympic-coder-32B](https://huggingface.co/YOYO-AI/QwQ-Olympic-coder-32B) ### Configuration The following YAML configuration was used to produce this model: ```yaml merge_method: sce models: # Pivot model - model: Qwen/Qwen2.5-Coder-32B # Target models - model: YOYO-AI/QwQ-Olympic-coder-32B - model: YOYO-AI/QwQ-openhands-coder-32B - model: YOYO-AI/QwQ-coder-32B - model: Qwen/QwQ-32B base_model: Qwen/Qwen2.5-Coder-32B parameters: select_topk: 1 dtype: bfloat16 tokenizer_source: Qwen/QwQ-32B normalize: true int8_mask: true ```