快速玩转 Llama2！机器学习 PAI 最佳实践（二）—全参数微调训练

import os
dsw_region = os.environ.get("dsw_region")
url_link = {
    "cn-shanghai": "https://atp-modelzoo-sh.oss-cn-shanghai-internal.aliyuncs.com/release/tutorials/llama2/llama2-7b.tar.gz",
    "cn-hangzhou": "https://atp-modelzoo.oss-cn-hangzhou-internal.aliyuncs.com/release/tutorials/llama2/llama2-7b.tar.gz",
    "cn-shenzhen": "https://atp-modelzoo-sz.oss-cn-shenzhen-internal.aliyuncs.com/release/tutorials/llama2/llama2-7b.tar.gz",
    "cn-beijing": "https://atp-modelzoo-bj.oss-cn-beijing-internal.aliyuncs.com/release/tutorials/llama2/llama2-7b.tar.gz", 
}
path = url_link[dsw_region]
os.environ['LINK_CHAT'] = path
!wget $LINK_CHAT
!tar -zxvf llama2-7b.tar.gz

! wget https://atp-modelzoo-sh.oss-cn-shanghai.aliyuncs.com/release/tutorials/llama2/ColossalAI.tar.gz
! tar -zxvf ColossalAI.tar.gz
! pip install ColossalAI/.
! pip install ColossalAI/applications/Chat/.
! pip install transformers==4.30.0
! pip install gradio==3.11

! wget https://atp-modelzoo-sh.oss-cn-shanghai.aliyuncs.com/release/tutorials/llama2/llama_data.json
! wget https://atp-modelzoo-sh.oss-cn-shanghai.aliyuncs.com/release/tutorials/llama2/llama_test.json

! sh ColossalAI/applications/Chat/examples/train_sft.sh

import gradio as gr
import requests
import json
from transformers import AutoTokenizer, AutoModelForCausalLM
#模型地址替换为自己训练好的模型地址
tokenizer = AutoTokenizer.from_pretrained("/mnt/workspace/sft_llama2-7b",trust_remote_code=True)
#模型地址替换为自己训练好的模型地址
model = AutoModelForCausalLM.from_pretrained("/mnt/workspace/sft_llama2-7b",trust_remote_code=True).eval().half().cuda()
def inference(text):
    from transformers import pipeline
    pipe = pipeline("text-generation", model=model, tokenizer=tokenizer,device='cuda:0', max_new_tokens=400)
    res=pipe(text)
    return res[0]['generated_text'][len(text):]
demo = gr.Blocks()
with demo:
    input_prompt = gr.Textbox(label="请输入需求", value="请以软件工程师的身份，写一篇入职的发言稿。", lines=6)
    generated_txt = gr.Textbox(lines=6)
    b1 = gr.Button("发送")
    b1.click(inference, inputs=[input_prompt], outputs=generated_txt) 
demo.launch(enable_queue=True, share=True)

# encoding=utf-8
import oss2
import os
AK='yourAccessKeyId'
SK='yourAccessKeySecret'
endpoint = 'yourEndpoint'
dir='your model output dir'
auth = oss2.Auth(AK, SK)
bucket = oss2.Bucket(auth, endpoint, 'examplebucket')
for filename in os.listdir(dir):
    current_file_path = dir+filename
    file_path = '需要上传地址'
    bucket.put_object_from_file(file_path, current_file_path)