本地部署大语言模型-DeepSeek
DeepSeek 是国内顶尖 AI 团队「深度求索」开发的多模态大模型,具备数学推理、代码生成等深度能力,堪称"AI界的六边形战士"。
Hostease AMD 9950X/96G/3.84T NVMe/1G/5IP/RTX4090 GPU服务器提供多种计费模式。
DeepSeek-R1-32B配置
配置项 | 规格要求 |
CPU | 16 核以上(如 AMD Ryzen 9950) |
内存 | 96GB |
硬盘 | 960GB |
显卡 | 24GB+ 显存(如 RTX 4090) |
# cat cpuinfo |grep name|head -1
model name : AMD Ryzen 9 9950X 16-Core Processor
# nvidia-smi
Sun Mar 2 14:51:30 2025
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.183.01 Driver Version: 535.183.01 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 4090 Off | 00000000:01:00.0 Off | Off |
| 0% 27C P8 5W / 450W | 495MiB / 24564MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
安装步骤(略写)
apt update
apt install nvidia-driver-535 -y
curl -fsSL https://ollama.com/install.sh | sh
ollama run deepseek-r1:32b-qwen-distill-q4_K_M --verbose
创建对话返回结果
>>> which is bigger,9.8 or 9.11?
<think>
Alright, so I'm trying to figure out whether 9.8 is bigger than 9.11 or not. At first glance, it seems like both numbers are pretty close to each
other since they both start with a 9 and then have some decimal parts. But wait, maybe there's something more to it.Okay, let me break this down step by step. First, I need to understand what these decimals represent. So, 9.8 can be read as nine plus eight
tenths, right? And 9.11 is nine plus eleven hundredths. Hmm, that makes sense. Now, the question is asking which one is bigger.Maybe it would help if I line them up vertically to compare the digits after the decimal point more easily:```9.809.11
```By adding a zero to 9.8 to make it 9.80, we can see that both numbers have two decimal places now. This should make the comparison straightforward.Now, let's look at the tenths place first:- For 9.80, the tenths digit is 8.
- For 9.11, the tenths digit is 1.Okay, so right here, it seems like 8 is greater than 1. That would mean that 9.80 is bigger because its tenths place is larger than the tenths
place of 9.11.But wait a second—is there something else I should consider? Maybe rounding or anything like that?Well, since both numbers are already given to two decimal places and we've added an extra zero to make them consistent, I think it's safe to say
that no further adjustment is necessary.Still, just to be thorough, let me convert these decimals into fractions to see if there's a difference in their values.For 9.80:- 0.80 as a fraction is the same as \( \frac{80}{100} \), which simplifies down to \( \frac{4}{5} \).So, 9.80 is equal to \( 9 + \frac{4}{5} = \frac{45}{5} + \frac{4}{5} = \frac{49}{5} \).For 9.11:- 0.11 as a fraction is approximately \( \frac{11}{100} \).So, 9.11 is equal to \( 9 + \frac{11}{100} = \frac{900}{100} + \frac{11}{100} = \frac{911}{100} \).Now, let's compare these two fractions:- \( \frac{49}{5} = 9.8 \)
- \( \frac{911}{100} = 9.11 \)To see which one is bigger, I can convert both to have the same denominator or find a common basis for comparison.Let's try finding equivalent fractions with the same denominator:The denominators are 5 and 100. Since 100 is a multiple of 5 (specifically, \( \frac{100}{5} = 20 \)), I'll convert both fractions to have a
denominator of 100.For \( \frac{49}{5} \):- Multiply numerator and denominator by 20: \( \frac{49 \times 20}{5 \times 20} = \frac{980}{100} \).So, \( \frac{49}{5} = \frac{980}{100} \).Now we have:- \( \frac{980}{100} \) (which is 9.8)
- \( \frac{911}{100} \) (which is 9.11)Comparing the numerators directly, since both fractions have the same denominator:- 980 > 911This means that \( \frac{980}{100} > \frac{911}{100} \), or in other words, 9.8 is greater than 9.11.Wait a minute—this contradicts what I thought earlier where the tenths place indicated that 9.8 was bigger because of having an 8 instead of a 1 in
the tenths place. But when converting to fractions with the same denominator, it's clear that even though both numbers have nine as their whole
number part, the decimal parts make a difference.But according to my calculations:- 9.8 is larger than 9.11 because \( \frac{49}{5} \) (or \( \frac{980}{100} \)) is greater than \( \frac{911}{100} \).So, this further confirms that 9.8 is bigger.Is there anything else I need to consider? Maybe looking at the hundredths place?Well, since we've already converted both numbers to have the same denominator and confirmed that 9.8 has a larger numerator in the hundredths place
as well (\( \frac{980}{100} \) vs. \( \frac{911}{100} \)), I think we can confidently say that 9.8 is indeed bigger than 9.11.Additionally, thinking about it on a number line might help visualize this:- If you imagine the numbers from 9 to 10:- 9.8 would be closer to 10.- 9.11 would be much closer to 9.Therefore, 9.8 is further along towards 10 and thus larger than 9.11.But just to ensure there's no mistake in the fraction conversion, let me double-check:- \( \frac{49}{5} = 9.8 \) since \( 49 ÷ 5 = 9.8 \).That seems correct because 5 times 9 is 45, and 49 minus 45 leaves a remainder of 4, so \( \frac{4}{5} = 0.8 \), making it 9.8.And for \( \frac{911}{100} \):- \( 911 ÷ 100 = 9.11 \).Yes, that's accurate because dividing by 100 moves the decimal point two places to the left.So everything checks out mathematically.Is there any alternative way to think about this?Perhaps considering money as an analogy:- If you have $9.80 and $9.11:- You'd obviously have more with $9.80 than with $9.11.This real-world scenario aligns with the mathematical conclusion that 9.8 is bigger.Alternatively, think of it in terms of measurements:- If something measures 9.8 centimeters and another measures 9.11 centimeters:- The first one would be longer than the second one.All these analogies reinforce the idea that 9.8 is indeed larger than 9.11.So, after carefully analyzing through different methods—decimal comparison, fraction conversion, number line visualization, and real-life
analogies—it becomes clear that 9.8 is bigger than 9.11.
</think>To determine which number is larger between \( 9.8 \) and \( 9.11 \), we can follow these steps:1. **Understand the Numbers**:- \( 9.8 \) is equivalent to \( 9.80 \).- Both numbers have a whole number part of 9.2. **Compare the Decimal Parts**:- The decimal part of \( 9.8 \) (or \( 9.80 \)) is 0.80.- The decimal part of \( 9.11 \) is 0.11.- Since \( 0.80 > 0.11 \), the decimal part of \( 9.8 \) is larger.3. **Conclusion**:- Therefore, \( 9.8 \) is bigger than \( 9.11 \).Final Answer:
\[
\boxed{9.8}
\]eval count: 501 token(s)
eval duration: 12.478s
eval rate: 40.15 tokens/s>>>
Web页面返回对话,2个数字比大小结果
相关文章:

本地部署大语言模型-DeepSeek
DeepSeek 是国内顶尖 AI 团队「深度求索」开发的多模态大模型,具备数学推理、代码生成等深度能力,堪称"AI界的六边形战士"。 Hostease AMD 9950X/96G/3.84T NVMe/1G/5IP/RTX4090 GPU服务器提供多种计费模式。 DeepSeek-R1-32B配置 配置项 规…...

adb的安装
1、概念 (1)adb(android debug bridge)安卓调试桥,用于完成电脑和手机之间的通信控制。 (2)xcode来完成对于ios设备的操控,前提是有个mac电脑。 2、adb的安装 (1&…...
Python 如何实现 Markdown 记账记录转 Excel 存储
文章精选推荐 1 JetBrains Ai assistant 编程工具让你的工作效率翻倍 2 Extra Icons:JetBrains IDE的图标增强神器 3 IDEA插件推荐-SequenceDiagram,自动生成时序图 4 BashSupport Pro 这个ides插件主要是用来干嘛的 ? 5 IDEA必装的插件&…...
随机播放音乐 伪随机
import java.util.*;/*** https://cloud.tencent.com.cn/developer/news/1045747* 伪随机播放音乐*/ public class MusicPlayer {private List<String> allSongs; // 所有歌曲列表private List<String> playedSongs; // 已经播放过的歌曲列表private Map<String…...
latex 环境配置
编译器可选 miktex和 tex live ① miktex 下载地址 Portable 版本用的也是 Installer版的安装程序 basic-miktex-24.1-x64.exe,但是需要修改文件名为 miktex-portable.exe ├──texmfs │ ├─config │ ├─data │ └─install │ └─miktex/…...
fortify安全扫描Access Control: Database问题解决
概述 Access Control: Database说白了就是权限控制。在访问数据库(sql和nosql)需要加入当前用户的权限控制。不然会被fortify扫描出来,认为客户端可能不挟持和假冒,从而导致数据被泄露。 但是这个并不是任何时候都需要的,有的接口本来…...

Java 设计模式:软件开发的精髓与艺
目录 一、设计模式的起源二、设计模式的分类1. 创建型模式2. 结构型模式3. 行为型模式三、设计模式的实践1. 单例模式2. 工厂模式3. 策略模式四、设计模式的优势五、设计模式的局限性六、总结在软件开发的浩瀚星空中,设计模式犹如一颗颗璀璨的星辰,照亮了开发者前行的道路。它…...

初学者如何用 Python 写第一个爬虫?
?? 欢迎来到我的博客! 非常高兴能在这里与您相遇。在这里,您不仅能获得有趣的技术分享,还能感受到轻松愉快的氛围。无论您是编程新手,还是资深开发者,都能在这里找到属于您的知识宝藏,学习和成长。 ?? …...
Cocos Creator3.8.6拖拽物体的几种方式
文章目录 前言一、第一种通过UILocation二、第二种通过UIDelta实现总结 前言 在游戏开发中,拖拽物体是一个非常常见的交互功能,无论是用于UI元素的拖动,还是场景中物体的移动,拖拽操作都能极大地提升用户体验。Cocos Creator 3.8…...
分布式Session
我用「餐厅点餐代码实战」帮你彻底搞懂分布式Session,看完不仅能应对面试,还能直接应用到实际开发。先记住这个核心矛盾:多服务员如何记住同一顾客的喜好? 一、从生活场景理解Session的本质 传统单机场景(小餐馆&…...
Kotlin 运算符重载
在Kotlin中,常用的运算符重载函数名如下: 1.算术操作符: 加法:plus 减法:minus 乘法:times 除法:div 取模:rem 或 mod 整数除法:floorDiv 求幂:pow 自增&…...

OpenHarmony4.1-轻量与小型系统ubuntu开发环境
因OpenHarmony官网提供包含轻量、小型与标准系统的全量代码非常宠大,解包后大概需要70G以上硬盘空间,如要编译标准系统则需要140G以上空间。 如硬盘空间有限与只使用轻量/小型OpenHarmony系统,则可以下载并直接使用本人裁剪源码过的ubuntu硬盘…...

AVR 单片机硬件供电处理
摘自AVR 单片机应用笔记:AN2519 - AVR Microcontroller Hardware Design Considerations。 2. 供电 供电设计是任何硬件设计的关键一环,直接影响到系统的性能。在设计供电时,有两个重要的方面需要考虑:ESD 防护和噪声干扰。这些内…...
LeetCode 27 移除元素
LeetCode 27 - 移除元素(Remove Element)是一个简单但经典的双指针问题,主要考察数组操作的基本功。虽然问题容易,但掌握多种解法以及衍生的变体问题对解决更复杂的操作数组问题有帮助。 题目描述 输入:整数数组 nums…...
对“预训练”的理解
预训练有什么用 传统的机器学习是偏数学的,对数据的量不做过多要求,而深度学习的项目通常是有大量的数据可供使用。 在平常的任务或者项目中,我们可能并没有大量数据,只有少量数据,在这时我们就可以通过“借用”有大…...

论文阅读:CAN GENERATIVE LARGE LANGUAGE MODELS PERFORM ASR ERROR CORRECTION?
CAN GENERATIVE LARGE LANGUAGE MODELS PERFORM ASR ERROR CORRECTION? 生成式大语言模型能否进行自动语音识别(ASR)纠错? https://arxiv.org/pdf/2307.04172 文章目录 速览常规总结通俗版 摘要(Abstract)2. 引言&a…...
Stable Diffusion(SD)系列模型及关联算法深度解析
一、基础模型架构演进 SD v1.5 核心架构:基于Latent Diffusion Model(LDM),通过VAE将图像压缩至潜空间进行扩散训练,支持512x512分辨率生成,兼容二次元与写实风格混合创作12。 训练数据&…...

FPGA开发,使用Deepseek V3还是R1(3):系统级与RTL级
以下都是Deepseek生成的答案 FPGA开发,使用Deepseek V3还是R1(1):应用场景 FPGA开发,使用Deepseek V3还是R1(2):V3和R1的区别 FPGA开发,使用Deepseek V3还是R1&#x…...
logback日志输出配置范例
logback日志输出配置范例 在wutool中,提供了logback日志输出配置范例,实现日志文件大小限制、滚动覆盖策略、定时清理等功能。 关于wutool wutool是一个java代码片段收集库,针对特定场景提供轻量解决方案,只要按需选择代码片段…...

【开源免费】基于SpringBoot+Vue.JS酒店管理系统(JAVA毕业设计)
本文项目编号 T 224 ,文末自助获取源码 \color{red}{T224,文末自助获取源码} T224,文末自助获取源码 目录 一、系统介绍二、数据库设计三、配套教程3.1 启动教程3.2 讲解视频3.3 二次开发教程 四、功能截图五、文案资料5.1 选题背景5.2 国内…...

【人工智能】神经网络的优化器optimizer(二):Adagrad自适应学习率优化器
一.自适应梯度算法Adagrad概述 Adagrad(Adaptive Gradient Algorithm)是一种自适应学习率的优化算法,由Duchi等人在2011年提出。其核心思想是针对不同参数自动调整学习率,适合处理稀疏数据和不同参数梯度差异较大的场景。Adagrad通…...

循环冗余码校验CRC码 算法步骤+详细实例计算
通信过程:(白话解释) 我们将原始待发送的消息称为 M M M,依据发送接收消息双方约定的生成多项式 G ( x ) G(x) G(x)(意思就是 G ( x ) G(x) G(x) 是已知的)࿰…...

UE5 学习系列(三)创建和移动物体
这篇博客是该系列的第三篇,是在之前两篇博客的基础上展开,主要介绍如何在操作界面中创建和拖动物体,这篇博客跟随的视频链接如下: B 站视频:s03-创建和移动物体 如果你不打算开之前的博客并且对UE5 比较熟的话按照以…...
1688商品列表API与其他数据源的对接思路
将1688商品列表API与其他数据源对接时,需结合业务场景设计数据流转链路,重点关注数据格式兼容性、接口调用频率控制及数据一致性维护。以下是具体对接思路及关键技术点: 一、核心对接场景与目标 商品数据同步 场景:将1688商品信息…...
Linux简单的操作
ls ls 查看当前目录 ll 查看详细内容 ls -a 查看所有的内容 ls --help 查看方法文档 pwd pwd 查看当前路径 cd cd 转路径 cd .. 转上一级路径 cd 名 转换路径 …...

从零开始打造 OpenSTLinux 6.6 Yocto 系统(基于STM32CubeMX)(九)
设备树移植 和uboot设备树修改的内容同步到kernel将设备树stm32mp157d-stm32mp157daa1-mx.dts复制到内核源码目录下 源码修改及编译 修改arch/arm/boot/dts/st/Makefile,新增设备树编译 stm32mp157f-ev1-m4-examples.dtb \stm32mp157d-stm32mp157daa1-mx.dtb修改…...
三体问题详解
从物理学角度,三体问题之所以不稳定,是因为三个天体在万有引力作用下相互作用,形成一个非线性耦合系统。我们可以从牛顿经典力学出发,列出具体的运动方程,并说明为何这个系统本质上是混沌的,无法得到一般解…...
【RockeMQ】第2节|RocketMQ快速实战以及核⼼概念详解(二)
升级Dledger高可用集群 一、主从架构的不足与Dledger的定位 主从架构缺陷 数据备份依赖Slave节点,但无自动故障转移能力,Master宕机后需人工切换,期间消息可能无法读取。Slave仅存储数据,无法主动升级为Master响应请求ÿ…...

华为云Flexus+DeepSeek征文|DeepSeek-V3/R1 商用服务开通全流程与本地部署搭建
华为云FlexusDeepSeek征文|DeepSeek-V3/R1 商用服务开通全流程与本地部署搭建 前言 如今大模型其性能出色,华为云 ModelArts Studio_MaaS大模型即服务平台华为云内置了大模型,能助力我们轻松驾驭 DeepSeek-V3/R1,本文中将分享如何…...

网站指纹识别
网站指纹识别 网站的最基本组成:服务器(操作系统)、中间件(web容器)、脚本语言、数据厍 为什么要了解这些?举个例子:发现了一个文件读取漏洞,我们需要读/etc/passwd,如…...