官方在输出模板中似乎加了这些内容
Additionally, we have observed that the DeepSeek-R1 series models tend to bypass thinking pattern (i.e., outputting “\n\n”) when responding to certain queries, which can adversely affect the model’s performance. To ensure that the model engages in thorough reasoning, we recommend enforcing the model to initiate its response with “\n” at the beginning of every output.
deepseek-ai/DeepSeek-R1 · Hugging Face — deepseek-ai/DeepSeek-R1 · Hugging Face
截图上面的其他模型似乎并没有
<think>(\n)
而是直接输出内容、或是同一行输出 <think></think> ，符合官方说的缺失思考过程的情况