1.Demo实战任务内容
2.部署 InternLM2-Chat-1.8B
模型进行智能对话
2.1配置环境
2.1.1创建开发机
创建自己的开发机并且取名字,这里取位lee,使用Cuda11.7-conda
镜像,调整配置为10% A100 * 1,随后进入开发机。
2.1.2配置环境
进入terminal(控制台)输入以下命令
studio-conda -o internlm-base -t demo
# 与 studio-conda 等效的配置方案
# conda create -n demo python==3.10 -y
# conda activate demo
# conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia
进入conda环境
conda activate demo
安装环境所需要的包
pip install huggingface-hub==0.17.3
pip install transformers==4.34
pip install psutil==5.9.8
pip install accelerate==0.24.1
pip install streamlit==1.32.2
pip install matplotlib==3.8.3
pip install modelscope==1.9.5
pip install sentencepiece==0.1.99
安装截图如下:
2.2下载 InternLM2-Chat-1.8B
模型
2.2.1按照路径创建文件夹
mkdir -p /root/demo
touch /root/demo/cli_demo.py
touch /root/demo/download_mini.py
cd /root/demo
进入demo文件,打开/root/demo/download_mini.py文件,复制以下代码进入文件中
import os
from modelscope.hub.snapshot_download import snapshot_download
# 创建保存模型目录
os.system("mkdir /root/models")
# save_dir是模型保存到本地的目录
save_dir="/root/models"
snapshot_download("Shanghai_AI_Laboratory/internlm2-chat-1_8b",
cache_dir=save_dir,
revision='v1.1.0')
2.2.2执行命令,下载模型参数文件:
python /root/demo/download_mini.py
运行效果:
2.3 运行 cli_demo
2.3.1打开/root/demo/cli_demo.py
文件
复制以下代码:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name_or_path = "/root/models/Shanghai_AI_Laboratory/internlm2-chat-1_8b"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True, device_map='cuda:0')
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='cuda:0')
model = model.eval()
system_prompt = """You are an AI assistant whose name is InternLM (书生·浦语).
- InternLM (书生·浦语) is a conversational language model that is developed by Shanghai AI Laboratory (上海人工智能实验室). It is designed to be helpful, honest, and harmless.
- InternLM (书生·浦语) can understand and communicate fluently in the language chosen by the user such as English and 中文.
"""
messages = [(system_prompt, '')]
print("=============Welcome to InternLM chatbot, type 'exit' to exit.=============")
while True:
input_text = input("\nUser >>> ")
input_text = input_text.replace(' ', '')
if input_text == "exit":
break
length = 0
for response, _ in model.stream_chat(tokenizer, input_text, messages):
if response is not None:
print(response[length:], flush=True, end="")
length = len(response)
2.3.2进入环境并且运行程序
conda activate demo
python /root/demo/cli_demo.py
效果如下:
2.3.3 测试模型
输入“请创作一个 300 字的小故事”
模型可以跑出,完成!
3 实战:部署实战营优秀作品 八戒-Chat-1.8B
模型
3.1配置环境
conda activate demo
3.2使用 git
命令来获得仓库内的 Demo 文件
cd /root/
git clone https://gitee.com/InternLM/Tutorial -b camp2
# git clone https://github.com/InternLM/Tutorial -b camp2
cd /root/Tutorial
效果如图:
3.3 下载运行demo
python /root/Tutorial/helloworld/bajie_download.py
随后输入:
streamlit run /root/Tutorial/helloworld/bajie_chat.py --server.address 127.0.0.1 --server.port 6006
3.4端口环境配置本地powershell
查询自己的端口,下图所示这里为41045,并且记住这个数据,将下列代码改为自己的端口
# 从本地使用 ssh 连接 studio 端口
# 将下方端口号 38374 替换成自己的端口号
ssh -CNg -L 6006:127.0.0.1:6006 root@ssh.intern-ai.org.cn -p 41045
查看自己的密码,并且复制粘贴到password后,并且回车
3.5运行成果
3.5.1打开http://127.0.0.1:6006 ,等待模型加载成功
输入测试“请自我介绍”得到输出成果
模型跑出,完成训练!