轻松玩转书生·浦语大模型趣味Demo
1 大模型及 InternLM 模型简介
1.1 什么是大模型?
大模型通常指的是人工智能领域中参数数量巨大、拥有庞大计算能力和参数规模的模型。
大模型的特点及应用:利用大量数据进行训练;拥有数十亿甚至数千亿个参数;模型在各种任务中展现出惊人的性能。
1.2 InternLM 模型全链条开源
2 InternLM-Chat-7B 智能对话 Demo
本节将介绍如何使用 InternStudio中的 A100(1/4)GPU和 InternLM-Chat-7B 模型部署一个智能对话 Demo。
2.1 模型介绍
2.2 环境准备
在 InternStudio 平台中选择 A100(1/4) 的配置,镜像选择 Cuda11.7-conda,如下图所示:
接下来进入开发机,并且打开其中的终端开始环境配置、模型下载和运行 demo。
首先,在终端输入 bash 命令,进入 conda 环境,然后使用以下命令从本地克隆一个已有的 pytorch 2.0.1 的环境:
bash # 请每次使用 jupyter lab 打开终端时务必先执行 bash 命令进入 bash 中
/root/share/install_conda_env_internlm_base.sh internlm-demo
然后使用以下命令激活环境:
conda activate internlm-demo
并在环境中安装运行 demo 所需要的依赖:
# 升级pip
python -m pip install --upgrade pip
pip install modelscope==1.9.5
pip install transformers==4.35.2
pip install streamlit==1.24.0
pip install sentencepiece==0.1.99
pip install accelerate==0.24.1
2.3 模型下载
InternStudio 平台的 share 目录下已经准备了全系列的 InternLM 模型,所以直接复制即可。使用如下命令复制:
mkdir -p /root/model/Shanghai_AI_Laboratory
cp -r /root/share/temp/model_repos/internlm-chat-7b /root/model/Shanghai_AI_Laboratory
-r 选项表示递归地复制目录及其内容
2.4 代码准备
首先 clone 代码,在 /root 路径下新建 code 目录,然后切换路径, clone 代码:
mkdir -p /root/code/
cd /root/code
git clone https://gitee.com/internlm/InternLM.git
切换 commit 版本,与教程 commit 版本保持一致:
cd InternLM
git checkout 3028f07cb79e5b1d7342f4ad8d11efad3fd13d17
将 /root/code/InternLM/web_demo.py
中 29 行和 33 行的模型更换为本地的 /root/model/Shanghai_AI_Laboratory/internlm-chat-7b
,记得保存文件!
2.5 终端运行
首先切换为VSCode模式,在 /root/code/InternLM
目录下新建一个 cli_demo.py
文件,将以下代码填入其中:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name_or_path = "/root/model/Shanghai_AI_Laboratory/internlm-chat-7b"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
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("User >>> ")
input_text = input_text.replace(' ', '')
if input_text == "exit":
break
response, history = model.chat(tokenizer, input_text, history=messages)
messages.append((input_text, response))
print(f"robot >>> {response}")
然后激活internlm-demo
环境,在终端运行以下命令:
python /root/code/InternLM/cli_demo.py
,即可体验 InternLM-Chat-7B 模型的对话能力。对话效果如下所示:
2.6 web demo 运行(基础作业1)
首先运行 /root/code/InternLM
目录下的 web_demo.py
文件,输入以下命令:
cd /root/code/InternLM
streamlit run web_demo.py --server.address 127.0.0.1 --server.port 6006
。然后,根据教程5.2节配置本地端口,将端口映射到本地。最后,在本地浏览器输入 http://127.0.0.1:6006 ,模型开始加载,在加载完模型之后,就可以与 InternLM-Chat-7B 进行对话了,如下图所示:
3 Lagent 智能体工具调用 Demo (进阶作业2)
本节将介绍如何使用 InternStudio中的 A100(1/4)GPU、InternLM-Chat-7B 模型和Lagent 框架部署一个智能工具调用 Demo。
3.1 Lagent介绍
环境和模型已经在2.2和2.3节准备好了!
3.2 Lagent 安装
首先切换路径到 /root/code
克隆 lagent
仓库,并通过 pip install -e .
源码安装 Lagent
cd /root/code
git clone https://gitee.com/internlm/lagent.git
cd /root/code/lagent
git checkout 511b03889010c4811b1701abb153e02b8e94fb5e # 尽量保证和教程commit版本一致
pip install -e . # 源码安装
3.3 修改代码
直接将 /root/code/lagent/examples/react_web_demo.py
内容替换为以下代码:
import copy
import os
import streamlit as st
from streamlit.logger import get_logger
from lagent.actions import ActionExecutor, GoogleSearch, PythonInterpreter
from lagent.agents.react import ReAct
from lagent.llms import GPTAPI
from lagent.llms.huggingface import HFTransformerCasualLM
class SessionState:
def init_state(self):
"""Initialize session state variables."""
st.session_state['assistant'] = []
st.session_state['user'] = []
#action_list = [PythonInterpreter(), GoogleSearch()]
action_list = [PythonInterpreter()]
st.session_state['plugin_map'] = {
action.name: action
for action in action_list
}
st.session_state['model_map'] = {}
st.session_state['model_selected'] = None
st.session_state['plugin_actions'] = set()
def clear_state(self):
"""Clear the existing session state."""
st.session_state['assistant'] = []
st.session_state['user'] = []
st.session_state['model_selected'] = None
if 'chatbot' in st.session_state:
st.session_state['chatbot']._session_history = []
class StreamlitUI:
def __init__(self, session_state: SessionState):
self.init_streamlit()
self.session_state = session_state
def init_streamlit(self):
"""Initialize Streamlit's UI settings."""
st.set_page_config(
layout='wide',
page_title='lagent-web',
page_icon='./docs/imgs/lagent_icon.png')
# st.header(':robot_face: :blue[Lagent] Web Demo ', divider='rainbow')
st.sidebar.title('模型控制')
def setup_sidebar(self):
"""Setup the sidebar for model and plugin selection."""
model_name = st.sidebar.selectbox(
'模型选择:', options=['gpt-3.5-turbo','internlm'])
if model_name != st.session_state['model_selected']:
model = self.init_model(model_name)
self.session_state.clear_state()
st.session_state['model_selected'] = model_name
if 'chatbot' in st.session_state:
del st.session_state['chatbot']
else:
model = st.session_state['model_map'][model_name]
plugin_name = st.sidebar.multiselect(
'插件选择',
options=list(st.session_state['plugin_map'].keys()),
default=[list(st.session_state['plugin_map'].keys())[0]],
)
plugin_action = [
st.session_state['plugin_map'][name] for name in plugin_name
]
if 'chatbot' in st.session_state:
st.session_state['chatbot']._action_executor = ActionExecutor(
actions=plugin_action)
if st.sidebar.button('清空对话', key='clear'):
self.session_state.clear_state()
uploaded_file = st.sidebar.file_uploader(
'上传文件', type=['png', 'jpg', 'jpeg', 'mp4', 'mp3', 'wav'])
return model_name, model, plugin_action, uploaded_file
def init_model(self, option):
"""Initialize the model based on the selected option."""
if option not in st.session_state['model_map']:
if option.startswith('gpt'):
st.session_state['model_map'][option] = GPTAPI(
model_type=option)
else:
st.session_state['model_map'][option] = HFTransformerCasualLM(
'/root/model/Shanghai_AI_Laboratory/internlm-chat-7b')
return st.session_state['model_map'][option]
def initialize_chatbot(self, model, plugin_action):
"""Initialize the chatbot with the given model and plugin actions."""
return ReAct(
llm=model, action_executor=ActionExecutor(actions=plugin_action))
def render_user(self, prompt: str):
with st.chat_message('user'):
st.markdown(prompt)
def render_assistant(self, agent_return):
with st.chat_message('assistant'):
for action in agent_return.actions:
if (action):
self.render_action(action)
st.markdown(agent_return.response)
def render_action(self, action):
with st.expander(action.type, expanded=True):
st.markdown(
"<p style='text-align: left;display:flex;'> <span style='font-size:14px;font-weight:600;width:70px;text-align-last: justify;'>插 件</span><span style='width:14px;text-align:left;display:block;'>:</span><span style='flex:1;'>" # noqa E501
+ action.type + '</span></p>',
unsafe_allow_html=True)
st.markdown(
"<p style='text-align: left;display:flex;'> <span style='font-size:14px;font-weight:600;width:70px;text-align-last: justify;'>思考步骤</span><span style='width:14px;text-align:left;display:block;'>:</span><span style='flex:1;'>" # noqa E501
+ action.thought + '</span></p>',
unsafe_allow_html=True)
if (isinstance(action.args, dict) and 'text' in action.args):
st.markdown(
"<p style='text-align: left;display:flex;'><span style='font-size:14px;font-weight:600;width:70px;text-align-last: justify;'> 执行内容</span><span style='width:14px;text-align:left;display:block;'>:</span></p>", # noqa E501
unsafe_allow_html=True)
st.markdown(action.args['text'])
self.render_action_results(action)
def render_action_results(self, action):
"""Render the results of action, including text, images, videos, and
audios."""
if (isinstance(action.result, dict)):
st.markdown(
"<p style='text-align: left;display:flex;'><span style='font-size:14px;font-weight:600;width:70px;text-align-last: justify;'> 执行结果</span><span style='width:14px;text-align:left;display:block;'>:</span></p>", # noqa E501
unsafe_allow_html=True)
if 'text' in action.result:
st.markdown(
"<p style='text-align: left;'>" + action.result['text'] +
'</p>',
unsafe_allow_html=True)
if 'image' in action.result:
image_path = action.result['image']
image_data = open(image_path, 'rb').read()
st.image(image_data, caption='Generated Image')
if 'video' in action.result:
video_data = action.result['video']
video_data = open(video_data, 'rb').read()
st.video(video_data)
if 'audio' in action.result:
audio_data = action.result['audio']
audio_data = open(audio_data, 'rb').read()
st.audio(audio_data)
def main():
logger = get_logger(__name__)
# Initialize Streamlit UI and setup sidebar
if 'ui' not in st.session_state:
session_state = SessionState()
session_state.init_state()
st.session_state['ui'] = StreamlitUI(session_state)
else:
st.set_page_config(
layout='wide',
page_title='lagent-web',
page_icon='./docs/imgs/lagent_icon.png')
# st.header(':robot_face: :blue[Lagent] Web Demo ', divider='rainbow')
model_name, model, plugin_action, uploaded_file = st.session_state[
'ui'].setup_sidebar()
# Initialize chatbot if it is not already initialized
# or if the model has changed
if 'chatbot' not in st.session_state or model != st.session_state[
'chatbot']._llm:
st.session_state['chatbot'] = st.session_state[
'ui'].initialize_chatbot(model, plugin_action)
for prompt, agent_return in zip(st.session_state['user'],
st.session_state['assistant']):
st.session_state['ui'].render_user(prompt)
st.session_state['ui'].render_assistant(agent_return)
# User input form at the bottom (this part will be at the bottom)
# with st.form(key='my_form', clear_on_submit=True):
if user_input := st.chat_input(''):
st.session_state['ui'].render_user(user_input)
st.session_state['user'].append(user_input)
# Add file uploader to sidebar
if uploaded_file:
file_bytes = uploaded_file.read()
file_type = uploaded_file.type
if 'image' in file_type:
st.image(file_bytes, caption='Uploaded Image')
elif 'video' in file_type:
st.video(file_bytes, caption='Uploaded Video')
elif 'audio' in file_type:
st.audio(file_bytes, caption='Uploaded Audio')
# Save the file to a temporary location and get the path
file_path = os.path.join(root_dir, uploaded_file.name)
with open(file_path, 'wb') as tmpfile:
tmpfile.write(file_bytes)
st.write(f'File saved at: {file_path}')
user_input = '我上传了一个图像,路径为: {file_path}. {user_input}'.format(
file_path=file_path, user_input=user_input)
agent_return = st.session_state['chatbot'].chat(user_input)
st.session_state['assistant'].append(copy.deepcopy(agent_return))
logger.info(agent_return.inner_steps)
st.session_state['ui'].render_assistant(agent_return)
if __name__ == '__main__':
root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
root_dir = os.path.join(root_dir, 'tmp_dir')
os.makedirs(root_dir, exist_ok=True)
main()
3.4 Demo运行
streamlit run /root/code/lagent/examples/react_web_demo.py --server.address 127.0.0.1 --server.port 6006
采用与2.6节相同的方案,然后在本地浏览器输入 http://127.0.0.1:6006
,选择 InternLM 模型加载。 输入数学问题 已知 2x+3=10,求x
, 此时 InternLM-Chat-7B 模型理解题意生成解此题的 Python 代码,Lagent 调度送入 Python 代码解释器求出该问题的解
,如下图所示:
4 浦语·灵笔图文理解创作 Demo(进阶作业1)
本节将介绍如何使用 InternStudio中的 A100(1/4)* 2的机器和 InternLM-Xcomposer-7B 模型部署一个图文理解创作 Demo。
4.1 InternLM-Xcomposer-7B 模型介绍
4.2 环境准备
进入开发机,并在终端输入 bash 命令,进入 conda 环境,接下来就是安装依赖,使用以下命令从本地克隆一个已有的pytorch 2.0.1 的环境:
/root/share/install_conda_env_internlm_base.sh xcomposer-demo
然后使用以下命令激活环境:
conda activate xcomposer-demo
接下来运行以下命令,严格安装以下版本的 transformers、gradio 等依赖包:
pip install transformers==4.33.1 timm==0.4.12 sentencepiece==0.1.99 gradio==3.44.4 markdown2==2.4.10 xlsxwriter==3.1.2 einops accelerate
4.3 模型下载
InternStudio平台的 share 目录下已经准备了全系列的 InternLM 模型,所以直接复制即可。使用如下命令复制:
mkdir -p /root/model/Shanghai_AI_Laboratory
cp -r /root/share/temp/model_repos/internlm-xcomposer-7b /root/model/Shanghai_AI_Laboratory
4.4 代码准备
在 /root/code
目录下 git clone InternLM-XComposer
仓库的代码:
cd /root/code
git clone https://gitee.com/internlm/InternLM-XComposer.git
cd /root/code/InternLM-XComposer
git checkout 3e8c79051a1356b9c388a6447867355c0634932d # 最好保证和教程的 commit 版本一致
4.5 Demo运行
在终端运行以下代码:
python examples/web_demo.py --folder /root/model/Shanghai_AI_Laboratory/internlm-xcomposer-7b --num_gpus 1 --port 6006
这里 num_gpus 1 是因为InternStudio平台对于 A100(1/4)*2 识别仍为一张显卡。但如果有小伙伴课后使用两张 3090 来运行此 demo,仍需将 num_gpus 设置为 2 。
记得对新机器重新配置端口,在本地浏览器输入 http://127.0.0.1:6006 加载wep页面。输入星链新闻稿,一开始使用的edge浏览器,web界面只出现延迟,结果加载不出来:
终端出现以下错误提示:
按错误提示修改,仍然加载不出来输出,终端出现Could not create share link. Please check your internet connection or our status page: https://status.gradio.app.
错误提示,百度这句话,运行chmod +x /root/.local/lib/python3.10/site-packages/gradio/frpc_linux_amd64_v0.2
命令,好了终端无报错了,但是仍然加载不出来输出。**会不会是浏览器问题,因为有其他人成功!**更换chrome浏览器,成功!图文并茂文章创作如下所示:
多模态对话图文理解,如下所示:
5 通用环境配置
5.1 pip、conda 换源
5.1.1 pip换源
临时使用镜像源安装,如下所示:some-package 为你需要安装的包名
pip install -i https://mirrors.cernet.edu.cn/pypi/web/simple some-package
设置pip默认镜像源,升级 pip 到最新的版本 (>=10.0.0) 后进行配置,如下所示:
python -m pip install --upgrade pip
# 若默认源的网络连接较差,采用:
# python -m pip install -i https://mirrors.cernet.edu.cn/pypi/web/simple --upgrade pip
pip config set global.index-url https://mirrors.cernet.edu.cn/pypi/web/simple
5.1.1 conda换源
各系统都可以通过修改用户目录下的 .condarc 文件来使用镜像站,不同系统下的 .condarc 目录如下:
- Linux: ${HOME}/.condarc
- Windows: C:\Users<YourUserName>.condarc
快速配置:
cat <<'EOF' > ~/.condarc
channels:
- defaults
show_channel_urls: true
default_channels:
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2
custom_channels:
conda-forge: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
pytorch: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
EOF
注意:Windows系统下先执行conda config --set show_channel_urls yes
生成.condarc
文件之后再修改。
5.2 模型下载
5.2.1 利用Hugging Face下载
使用 Hugging Face 官方提供的 huggingface-cli 命令行工具。安装依赖:
pip install -U huggingface_hub
利用以下命令下载:
huggingface-cli download --resume-download internlm/internlm-chat-7b --local-dir your_path
其中 resume-download:断点续下, local-dir:本地存储绝对路径。
基础作业2:熟悉 hugging face 下载功能,使用 huggingface_hub python 包,下载 InternLM-20B 的 config.json 文件到本地:
首先下载huggingface_hub包,如下图所示:
然后把下载文件的代码写到download.py文件中,如下图所示:
利用huggingface的镜像,执行HF_ENDPOINT=https://hf-mirror.com python download.py
,如下图所示:
成功下载!