Add files via upload
添加本地部署fastapi
This commit is contained in:
parent
1862bbbd7d
commit
8d8cb07c59
85
deploy/api-file.py
Normal file
85
deploy/api-file.py
Normal file
@ -0,0 +1,85 @@
|
||||
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
|
||||
# 加载模型
|
||||
from transformers.utils import logging
|
||||
from openxlab.model import download
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
# 可修改
|
||||
download(model_repo='ajupyter/EmoLLM_aiwei',
|
||||
output='model')
|
||||
|
||||
# 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
|
||||
history = json_post_list.get('history') # 获取请求中的历史记录
|
||||
max_length = json_post_list.get('max_length') # 获取请求中的最大长度
|
||||
top_p = json_post_list.get('top_p') # 获取请求中的top_p参数
|
||||
temperature = json_post_list.get('temperature') # 获取请求中的温度参数
|
||||
# 调用模型进行对话生成
|
||||
response, history = model.chat(
|
||||
tokenizer,
|
||||
prompt,
|
||||
history=history,
|
||||
max_length=max_length if max_length else 2048, # 如果未提供最大长度,默认使用2048
|
||||
top_p=top_p if top_p else 0.7, # 如果未提供top_p参数,默认使用0.7
|
||||
temperature=temperature if temperature else 0.95 # 如果未提供温度参数,默认使用0.95
|
||||
)
|
||||
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,
|
||||
"history": history,
|
||||
"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() # 执行GPU内存清理
|
||||
return answer # 返回响应
|
||||
|
||||
# 主函数入口
|
||||
if __name__ == '__main__':
|
||||
# 加载预训练的分词器和模型
|
||||
tokenizer = AutoTokenizer.from_pretrained("model", trust_remote_code=True)
|
||||
model = (
|
||||
AutoModelForCausalLM.from_pretrained("model", device_map="auto", trust_remote_code=True)
|
||||
.to(torch.bfloat16)
|
||||
.cuda()
|
||||
)
|
||||
# model = AutoModelForCausalLM.from_pretrained("model", device_map="auto", trust_remote_code=True).eval()
|
||||
model.generation_config = GenerationConfig(max_length=2048, top_p=0.7, temperature=0.95) # 可指定
|
||||
model.eval() # 设置模型为评估模式
|
||||
# 启动FastAPI应用
|
||||
# 用6006端口可以将autodl的端口映射到本地,从而在本地使用api
|
||||
uvicorn.run(app, host='127.0.0.1', port=6006, workers=1) # 在指定端口和主机上启动应用
|
Loading…
Reference in New Issue
Block a user