前言
DeepSeek最近真的太火了，看了几篇教学都是用的ollama运行的demo，这篇笔记通过Python+HuggingFace运行跑一个demo。
第一次跑本地跑大模型，大佬勿喷哈。
安装依赖
pip install torch transformers accelerate uvicorn fastapi python-multipart huggingface_hub
下载模型
这里下载的是1.5B模型，其他可以参考：huggingface.co/deepseek-ai…
from huggingface_hub import snapshot_download
# 设置模型名称
model_id = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
# 下载模型到本地目录
local_dir = "./models/DeepSeek-R1-Distill-Qwen-1.5B"
snapshot_download(
repo_id=model_id,
local_dir=local_dir,
revision="main", # 模型版本（默认 main）
resume_download=True, # 断点续传
local_dir_use_symlinks=False # 直接复制文件，而非创建符号链接
)
print(f"模型已下载到：{local_dir}")
通过python运行，即可下载到本地。
效果
有时候回答会比较飘，加些限制会好很多。
代码
代码分为两块，一个前端文件，一个后端文件:
- main.py
- frontend.html
后端main.py
from fastapi import FastAPI, Request
from fastapi.responses import JSONResponse
from fastapi.responses import HTMLResponse
from fastapi.staticfiles import StaticFiles
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
app = FastAPI()
# 模型名称
model_name = "./models/DeepSeek-R1-Distill-Qwen-1.5B"
# 加载模型和分词器
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
device_map="auto", # 自动分配 GPU/CPU
torch_dtype=torch.float16, # 半精度推理（显存需求更低）
trust_remote_code=True # 信任自定义代码（如果模型需要）
)
# 提供静态文件（HTML/CSS/JS）
app.mount("/static", StaticFiles(directory="."), name="static")
# 返回前端页面
@app.get("/", response_class=HTMLResponse)
async def index():
with open("frontend.html", "r", encoding="utf-8") as f:
return f.read()
@app.post("/generate")
async def generate_text(request: Request):
data = await request.json()
prompt = data.get("prompt", "")
max_length = 2048
# 生成文本
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_length=max_length,
do_sample=True,
temperature=0.7
)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return JSONResponse({"generated_text": generated_text})
if __name__ == "__main__":
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=8000)
前端frontend.html
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<title>DeepSeek 对话助手</title>
<style>
body { font-family: Arial, sans-serif; max-width: 800px; margin: 0 auto; padding: 20px; background-color: #f0f2f5; }
#chat-container { background-color: white; border-radius: 10px; box-shadow: 0 2px 10px rgba(0,0,0,0.1); padding: 20px; }
#chat-history { height: 800px; overflow-y: auto; margin-bottom: 20px; border: 1px solid #ddd; padding: 10px; border-radius: 5px; }
.message { margin: 10px 0; padding: 8px 12px; border-radius: 15px; max-width: 70%; }
.user-message { background-color: #e3f2fd; margin-left: auto; }
.bot-message { background-color: #f5f5f5; margin-right: auto; }
#input-container { display: flex; gap: 10px; }
#user-input { flex: 1; padding: 10px; border: 1px solid #ddd; border-radius: 5px; }
button { padding: 10px 20px; background-color: #007bff; color: white; border: none; border-radius: 5px; cursor: pointer; }
button:hover { background-color: #0056b3; }
.think-content {
color: #666;
font-style: italic;
background-color: #f9f9f9;
padding: 5px;
border-radius: 5px;
margin: 5px 0;
}
.loading-message {
color: #666;
font-style: italic;
text-align: center;
padding: 10px;
animation: blink 1.5s infinite;
}
@keyframes blink {
0% { opacity: 0.6; }
50% { opacity: 1; }
100% { opacity: 0.6; }
}
</style>
</head>
<body>
<div id="chat-container">
<div id="chat-history"></div>
<div id="input-container">
<input type="text" id="user-input" placeholder="输入你的消息...">
<button onclick="sendMessage()">发送</button>
</div>
</div>
<script>
// 显示加载状态
function showLoading() {
const chatHistory = document.getElementById('chat-history');
const loading = document.createElement('div');
loading.id = 'loading';
loading.className = 'loading-message';
loading.textContent = '思考中...';
chatHistory.appendChild(loading);
scrollToBottom();
}
// 隐藏加载状态
function hideLoading() {
const loading = document.getElementById('loading');
if (loading) loading.remove();
}
// 原有消息处理函数保持不变
function scrollToBottom() {
const chatHistory = document.getElementById('chat-history');
chatHistory.scrollTop = chatHistory.scrollHeight;
}
function parseResponse(response) {
const thinkEnd = response.indexOf('</think>');
console.log(thinkEnd)
if (thinkEnd === -1) {
// 如果没有 think 标签，直接返回原始内容
return { main: response, think: null };
}
let parts = response.split("</think>");
// 提取 think 内容和主内容
const think = parts[0];
const main = parts[1];
return { main, think };
}
function addMessage(message, isUser = true) {
const chatHistory = document.getElementById('chat-history');
const messageDiv = document.createElement('div');
messageDiv.className = `message ${isUser ? 'user-message' : 'bot-message'}`;
// 解析消息内容
const { main, think } = parseResponse(message.replace(/\n/g, "<br>"));
// 显示主内容
messageDiv.innerHTML = main;
// 如果有 think 内容，用浅色标识
if (think) {
const thinkDiv = document.createElement('div');
thinkDiv.className = 'think-content';
thinkDiv.innerHTML = think;
messageDiv.appendChild(thinkDiv);
}
chatHistory.appendChild(messageDiv);
scrollToBottom();
}
async function sendMessage() {
const input = document.getElementById('user-input');
const message = input.value.trim();
if (!message) return;
input.value = '';
addMessage(message, true);
// 显示加载状态
showLoading();
try {
const response = await fetch('/generate', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ prompt: message, max_length: 500 })
});
if (!response.ok) throw new Error(`HTTP error! status: ${response.status}`);
const data = await response.json();
// 隐藏加载状态后显示回复
hideLoading();
addMessage(data.generated_text, false);
} catch (error) {
// 出错时也隐藏加载状态
hideLoading();
addMessage(`请求失败: ${error.message}`, false);
}
}
// 回车发送支持
document.getElementById('user-input').addEventListener('keypress', (e) => {
if (e.key === 'Enter') sendMessage();
});
</script>
</body>
</html>
