deepseek的对话风格

最新推荐文章于 2025-05-13 09:51:41 发布

nangonghen

最新推荐文章于 2025-05-13 09:51:41 发布

阅读量591

点赞数 3

分类专栏：大模型LLM 文章标签： deepseek 大模型

本文链接：https://blog.csdn.net/nangonghen/article/details/145445857

版权

大模型LLM 专栏收录该内容

15 篇文章

订阅专栏

概述

deepseek的对话风格，比一般的模型的回答多了思考过程，这是它比较可爱的地方，模型的回答有了思考过程，对用户而言大模型的回答不完全是一个黑盒。

deepseek的对话风格

train_prompt_style = """Below is an instruction that describes a task, paired with an input that provides further context.
Write a response that appropriately completes the request.
Before answering, think carefully about the question and create a step-by-step chain of thoughts to ensure a logical and accurate response.


### Instruction:
You are a medical expert with advanced knowledge in clinical reasoning, diagnostics, and treatment planning.
Please answer the following medical question.


### Question:
{}


### Response:
<think>
{}
</think>
{}"""

因此需要有一个程序，将数据集中的内容填充到上面的三个占位符{}中。