Qwen1.5-1.8b部署

最新推荐文章于 2024-12-05 14:49:53 发布

雾重烟秋

最新推荐文章于 2024-12-05 14:49:53 发布

阅读量966

点赞数 20

分类专栏：大语言模型实战文章标签： fastapi python 语言模型

本文链接：https://blog.csdn.net/a_blade_of_grass/article/details/140162084

版权

仿照ChatGLM3部署，参考了Qwen模型的文档，模型地址https://modelscope.cn/models/qwen/Qwen1.5-1.8B-Chat/summary

http接口

服务端代码api.py

from fastapi import FastAPI, Request
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
import uvicorn
import json
import datetime
import torch

# 设置设备参数
DEVICE = "cuda"  # 使用CUDA
DEVICE_ID = "0"  # CUDA设备ID，如果未设置则为空
CUDA_DEVICE = f"{
     DEVICE}:{
     DEVICE_ID}" if DEVICE_ID else DEVICE  # 组合CUDA设备信息

# 加载预训练的分词器和模型
model_name_or_path = '/root/autodl-tmp/qwen/Qwen1.5-1.8B-Chat'
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", torch_dtype=torch.bfloat16)

# 清理GPU内存函数
def torch_gc():
    if torch.cuda.is_available():  # 检查是否可用CUDA
        with torch.cuda.device(CUDA_DEVICE):  # 指定CUDA设备
            torch.cuda.empty_cache()  # 清空CUDA缓存
            torch.cuda.ipc_collect()  # 收集CUDA内存碎片

# 创建FastAPI应用
app = FastAPI()

# 处理POST请求的端点
@app.post("/")
async def create_item(request: Request):
    global model, tokenizer  # 声明全局变量以便在函数内部使用模型和分词器
    json_post_raw = await request.json()  # 获取POST请求的JSON数据
    json_post = json.dumps(json_post_raw)  # 将JSON数据转换为字符串
    json_post_list = json.loads(json_post)  # 将字符串转换为Python对象
    prompt = json_post_list.get('prompt')  # 获取请求中的提示

    messages = [
            {
   "role": "system", "content": "You are a helpful assistant."},
            {
   "role": "user", "content": prompt}
    ]

    # 调用模型进行对话生成
    input_ids = tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True)
    model_inputs = tokenizer([input_ids], return_tensors="pt").to('cuda')
    generated_ids = model.generate(model_inputs.input_ids,max_new_tokens=512)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]
    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    now = datetime.datetime.now()  # 获取当前时间
    time = now.strftime("%Y-%m-%d %H:%M:%S")  # 格式化时间为字符串
    # 构建响应JSON
    answer = {
   
        "response": response,
        "status": 200,
        "time": time
    }
    # 构建日志信息
    log = "[" + time + "] " + '", prompt:"' + prompt + '", response:"' + repr(response) + '"'
    print(log)  # 打印日志
    torch_gc