| models: | |
| - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 | |
| parameters: | |
| weight: 1.0 | |
| - model: cyberagent/DeepSeek-R1-Distill-Qwen-14B-Japanese | |
| parameters: | |
| weight: 1.0 | |
| merge_method: task_arithmetic | |
| base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | |
| dtype: bfloat16 | |
| tokenizer_source: base |