Notebook大模型训练步骤_notebook训练-优快云博客

一、Notebook环境运行服务体验

注册魔搭社区，关联阿里云帐号会赠送100个小时的GPU加速体验。

二、公开模型

可使用社区公开模型进行调用调试

有两种调用模式：

①直接调用模型使用本地算力或云服务器算力计算。

from modelscope.utils.constant import Tasks
from modelscope.pipelines import pipeline
import cv2

pipe = pipeline(task=Tasks.text_to_image_synthesis, 
                model='AI-ModelScope/stable-diffusion-v1-5',
                model_revision='v1.0.0')
prompt = 'a dog'
output = pipe({'text': prompt})
cv2.imwrite('result.png', output['output_imgs'][0])
from PIL import Image
from io import BytesIO
image = Image.fromarray(output['output_imgs'][0])
image.show()

②通过http的方式请求云端上已经私有化部署的大模型服务。每个用户每天有免费2000次token调用的请求限制。

import requests
import json
from PIL import Image
from io import BytesIO

url = "https://api-inference.modelscope.cn/v1/images/generations"
payload = {
    "model": 'MAILAND/majicflus_v1',#ModelScope Model-Id,required
    "prompt": "A golden cat"# required
}
headers = {
    "Authorization": "Bearer 646dbe2d-2590-4c4c-82f3-a2bfe71cdb77",
    "Content-Type": "application/json"
}
response = requests.post(url, data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers)
response_data = response.json()
image = Image.open(BytesIO(requests.get(response_data['images'][0]['url']).content))
image.save("result_image.jpg")