DeepSeek15天指导手册一从入门到精通

第一章：准备篇 (30分钟上手）

1.1三分钟创建你的AI伙伴

步骤详解：

1．访问官网：在浏览器输入「www.deepseek.com」 (就像打开微信一样简单)

2．注册账号：点击右上角「笑脸图标」 $\rightarrow$ 选择 「邮箱/手机注册」 (建议使用常用邮箱)

DeepSeek15天指导手册一从入门到精通

第一章：准备篇 (30分钟上手）

1.1三分钟创建你的AI伙伴

步骤详解：

1．访问官网：在浏览器输入「www.deepseek.com」 (就像打开微信一样简单)

2．注册账号：点击右上角「笑脸图标」 $\rightarrow$ 选择 「邮箱/手机注册」 (建议使用常用邮箱)

DeepSeek 15天指导手册——从入门到精通

第一章：准备篇 （30分钟上手）

1.1 三分钟创建你的AI伙伴

步骤详解：

1. 访问官网：在浏览器输入「www.deepseek.com」 （就像打开微信一样简单）

DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence

Daya Guo*1, Qihao Zhu∗1,2, Dejian Yang1, Zhenda Xie1, Kai Dong1, Wentao Zhang1
Guanting Chen1, Xiao Bi 1, Y. Wu1, Y.K. $\mathrm{L}\dot{\mathbf{i}}^{1}$ , Fuli Luo1, Yingfei Xiong2, Wenfeng Liang1

1DeepSeek-AI
2Key Lab of HCST (PKU), MOE; SCS, Peking University {zhuqh, guodaya}@deepseek.com
https://github.com/deepseek-ai/DeepSeek-Coder

Abstract

The rapid development of large language models has revolutionized code intelligence in software development. However, the predominance of closed-source models has restricted extensive research and development. To address this, we introduce the DeepSeek-Coder series, a range of open-source code models with sizes from 1.3B to 33B, trained from scratch on 2 trillion tokens. These models are pre-trained on a high-quality project-level code corpus and employ a fill-in-the-blank task with a 16K window to enhance code generation and infilling. Our extensive evaluations demonstrate that DeepSeek-Coder not only achieves state-of-the-art performance among open-source code models across multiple benchmarks but also surpasses existing closed-source models like Codex and GPT-3.5. Furthermore, DeepSeek-Coder models are under a permissive license that allows for both research and unrestricted commercial use.

DeepSeek LLM Scaling Open-Source Language Models with Longtermism

Xiao Bi, Deli Chen, Guanting Chen, Shanhuang Chen, Damai Dai, Chengqi Deng, Honghui Ding, Kai Dong, Qiushi Du, Zhe Fu, Huazuo Gao, Kaige Gao, Wenjun Gao,
Ruiqi Ge, Kang Guan, Daya Guo, Jianzhong Guo, Guangbo Hao, Zhewen Hao, Ying He,
Wenjie Hu, Panpan Huang, Erhang Li, Guowei Li, Jiashi Li, Yao Li, Y.K. Li, Wenfeng Liang, Fangyun Lin, A.X. Liu, Bo Liu, Wen Liu, Xiaodong Liu, Xin Liu, Yiyuan Liu, Haoyu Lu,
Shanghao Lu, Fuli Luo, Shirong Ma, Xiaotao Nie, Tian Pei, Yishi Piao, Junjie Qiu, Hui Qu, Tongzheng Ren, Zehui Ren, Chong Ruan, Zhangli Sha, Zhihong Shao, Junxiao Song,
Xuecheng Su, Jingxiang Sun, Yaofeng Sun, Minghui Tang, Bingxuan Wang, Peiyi Wang,
Shiyu Wang, Yaohui Wang, Yongji Wang, Tong Wu, Y. Wu, Xin Xie, Zhenda Xie, Ziwei Xie,
Yiliang Xiong, Hanwei Xu, R.X. Xu, Yanhong Xu, Dejian Yang, Yuxiang You, Shuiping Yu, Xingkai Yu, B. Zhang, Haowei Zhang, Lecong Zhang, Liyue Zhang, Mingchuan Zhang, Minghua Zhang, Wentao Zhang, Yichao Zhang, Chenggang Zhao, Yao Zhao, Shangyan Zhou, Shunfeng Zhou, Qihao Zhu, Yuheng Zou *

《Deepseek R1 本地部署完全⼿册》

版权归：HomeBrew Ai Club作者wechat：samirtan版本：V2.0更新⽇期：2025年2⽉8⽇

⼀、简介

Deepseek R1 是⽀持复杂推理、多模态处理、技术⽂档⽣成的⾼性能通⽤⼤语⾔模型。本⼿册为技术团队提供完整的本地部署指南，涵盖硬件配置、国产芯⽚适配、量化⽅案、云端替代⽅案及完整671B MoE模型的Ollama部署⽅法。

DeepSeek-R1是DeepSeek团队推出的第一代推理模型，通过强化学习（RL）和蒸馏技术显著提升

导语

了语言模型的推理能力。DeepSeek-R1-Zero模型在没有监督微调（SFT）的情况下，通过大规模强化学习训练展现出强大的推理能力，但存在可读性和语言混合问题。为了解决这些问题， DeepSeek-R1引入了冷启动数据和多阶段训练，推理性能与OpenAI的GPT o1-1217相当。此外，团队还科全书，欢迎对复杂性科学感兴趣、热爱知识整理和分享的朋友加入，文末可以扫码报名加入百科志愿者！

DeepSeek R1 实战技巧合集

B站/抖音/小红书/视频号/Youtube：秋芝2046

Deepseek使用途径

1. 官网及APP

网址： deepseek.com 及移动应用（iOS/Android）特征：完整版R1模型，支持深度搜索，但目前因流量大常遇到服务器繁忙问题。

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

DeepSeek-AI

research@deepseek.com

Abstract

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrates remarkable reasoning capabilities. Through RL, DeepSeek-R1-Zero naturally emerges with numerous powerful and intriguing reasoning behaviors. However, it encounters challenges such as poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates multi-stage training and cold-start data before RL. DeepSeekR1 achieves performance comparable to OpenAI-o1-1217 on reasoning tasks. To support the research community, we open-source DeepSeek-R1-Zero, DeepSeek-R1, and six dense models (1.5B, 7B, 8B, 14B, 32B, 70B) distilled from DeepSeek-R1 based on Qwen and Llama.

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

DeepSeek-AI

research@deepseek.com

Abstract

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrates remarkable reasoning capabilities. Through RL, DeepSeek-R1-Zero naturally emerges with numerous powerful and intriguing reasoning behaviors. However, it encounters challenges such as poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates multi-stage training and cold-start data before RL. DeepSeekR1 achieves performance comparable to OpenAI-o1-1217 on reasoning tasks. To support the research community, we open-source DeepSeek-R1-Zero, DeepSeek-R1, and six dense models (1.5B, 7B, 8B, 14B, 32B, 70B) distilled from DeepSeek-R1 based on Qwen and Llama.