#
操作系统为centos 9.
先安装驱动程序
#切换成文字界面
sudo systemctl set-default multi-user.target
sudo reboot
sh NVIDIA-Linux-x86_64-550.107.02.run
#切换成图形界面
sudo systemctl set-default graphical.target
sudo reboot
安装docker:
yum remove docker \
docker-client \
docker-client-latest \
docker-common \
docker-latest \
docker-latest-logrotate \
docker-logrotate \
docker-engine
yum install -y yum-utils
yum-config-manager --add-repo https://mirrors.tuna.tsinghua.edu.cn/docker-ce/linux/centos/docker-ce.repo
sed -i 's+https://download.docker.com+https://mirrors.tuna.tsinghua.edu.cn/docker-ce+' /etc/yum.repos.d/docker-ce.repo
yum install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
sudo nvidia-ctk runtime configure --runtime=docker
改镜像地址：
[paul@paul-pc ~]$ cat /etc/docker/daemon.json
{
"registry-mirrors": [
"http://xxx.xxx.xxx"
],
"runtimes": {
"nvidia": {
"args": [],
"path": "nvidia-container-runtime"
}
}
}
安装container-took-kit：
sh cuda_12.6.0_560.28.03_linux.run
验证：
sudo docker run --rm -it --gpus all ubuntu nvidia-smi
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.107.02 Driver Version: 550.107.02 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 2080 Ti Off | 00000000:01:00.0 On | N/A |
| 62% 36C P8 4W / 260W | 256MiB / 22528MiB | 1% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 1 NVIDIA GeForce RTX 2080 Ti Off | 00000000:02:00.0 Off | N/A |
| 64% 35C P8 5W / 260W | 9MiB / 22528MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 2657 G /usr/libexec/Xorg 99MiB |
| 0 N/A N/A 2735 G /usr/bin/gnome-shell 38MiB |
| 0 N/A N/A 3502 G /usr/lib64/firefox/firefox 111MiB |
| 1 N/A N/A 2657 G /usr/libexec/Xorg 4MiB |
+-----------------------------------------------------------------------------------------+
参考地址：
python服务器脚本，生成html，无需写js,css，适合AI项目
生成文字的代码：
st.text(
'Fixed width text')
st.markdown(
'_Markdown_')
# see #*
st.caption(
'Balloons. Hundreds of them
')
st.latex(r
''' e^{i\pi} + 1 = 0 ''')
st.write(
'Most objects')
# df, err, func, keras!
st.write([
'st',
'is <', 3])
# see *
st.title(
'My title')
st.header(
'My header')
st.subheader(
'My sub')
st.code(
'for i in range(8): foo()')
# * optional kwarg unsafe_allow_html = True
生成form控件：
st.button('Hit me')
st.data_editor('Edit data', data)
st.checkbox('Check me out')
st.radio('Pick one:', ['nose','ear'])
st.selectbox('Select', [1,2,3])
st.multiselect('Multiselect', [1,2,3])
st.slider('Slide me', min_value=0, max_value=10)
st.select_slider('Slide to select', options=[1,'2'])
st.text_input('Enter some text')
st.number_input('Enter a number')
st.text_area('Area for textual entry')
st.date_input('Date input')
st.time_input('Time entry')
st.file_uploader('File uploader')
st.download_button('On the dl', data)
st.camera_input("一二三,茄子!")
st.color_picker('Pick a color')
用表格显示数据：
st.dataframe(my_dataframe)
st.table(data.iloc[0:10])
st.json({'foo':'bar','fu':'ba'})
st.metric(label="Temp", value="273 K", delta="1.2 K")
显示加载进度条与状态：
# Show a spinner during a process
>>> with st.spinner(text='In progress'):
>>> time.sleep(3)
>>> st.success('Done')
# Show and update progress bar
>>> bar = st.progress(50)
>>> time.sleep(3)
>>> bar.progress(100)
st.balloons()
st.snow()
st.toast('Mr Stay-Puft')
st.error('Error message')
st.warning('Warning message')
st.info('Info message')
st.success('Success message')
st.exception(e)
这几天要PUSH代码到GITHUB，发现之前用的密码方式被取消了，需改成SSH KEY的方式。
1.生成SSH-KEY
ssh-keygen
#会产生 ~/.ssh/id_rsa 和 ~/.ssh/id_rsa_pub 文件
#如果是从别的地方拷贝过来的id_rsa，需chmod 400 ~/.ssh/id_rsa更改属性
2.在github上新建仓库
https://github.com/paulwong888/python-ai
3.导入公钥到github
打开你的SSH公钥文件，通常位于~/.ssh/id_rsa.pub。复制公钥内容，然后登录到你的GitHub账户，进入Settings > SSH and GPG keys，点击"New SSH key"按钮，粘贴你的公钥，然后点击"Add SSH key"。
4.克隆仓库
git config --global user.name "John Doe"
git config --global user.email johndoe@example.com
git clone git@github.com:paulwong888/python-ai
5.导入project到eclipse
上步克隆时已经在本地新建了一个本地仓库，Import->Git->Project from Git->Existing local repository，选择python-ai/.git文件夹
之后的操作和用密码的方式是一样的。
上篇已经合并出了训练好的大模型，现在要搭建起一套CHATBOT，使得这套大模型能有一个WEBUI用起来。
1.设置环境变量，ollama的模型保存路径，/etc/profile
export OLLAMA_MODELS=/root/autodl-tmp/models/ollama
2.克隆ollama代码
curl -fsSL https://ollama.com/install.sh | sh
3.启动ollama
4.建立ollama镜像的配置文件，Modelfile
# set the base model
FROM /root/.ollama/llamafactory-export/saves/llama3-8b/lora/docker-commnad-nlp/export
# set custom parameter values
PARAMETER temperature 1
PARAMETER num_keep 24
PARAMETER stop <|start_header_id|>
PARAMETER stop <|end_header_id|>
PARAMETER stop <|eot_id|>
PARAMETER stop <|reserved_special_token
# set the model template
TEMPLATE """
{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ .Response }}<|eot_id|>
"""
# set the system message
SYSTEM You are llama3 from Meta, customized and hosted @ Paul Wong (http://paulwong88.tpddns.cn).
# set Chinese lora support
#ADAPTER /root/.ollama/models/lora/ggml-adapter-model.bin
建立镜像命令，create-ollama-image-docker-command-nlp.sh
BIN_PATH=$(cd `dirname $0`; pwd)
cd $BIN_PATH/
pwd
ollama create llama3-docker-commnad-nlp:paul -f Modelfile
5.运行大模型
llama3-docker-commnad-nlp:paul
对于象META的开源大模型，如llama3，由于都是用通用数据进行预训练，对想使用其模型的公司来说，可能会不适用，因为这大模型对公司的数据不熟悉，因此引入微调(Fine-Tunning)。
通过喂给大模型大量数据，1万条起步，使得大模型也能对公司的数据熟悉，进而用于各种对话场景。
1.克隆并安装LLAMA FACTORY库，install-llamafactory.sh
BIN_PATH=$(cd `dirname $0`; pwd)
cd $BIN_PATH/../
pwd
git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
cd LLaMA-Factory
pip install -e ".[torch,metrics,bitsandbytes,modelscope]"
2.设置环境变量
export USE_MODELSCOPE_HUB=1 #使用modelscop模型库，非huggingface的
export CUDA_VISIBLE_DEVICES=0 ＃设置使用GPU
export HF_ENDPOINT=https://hf-mirror.com ＃设置huggingface的替代地址
export MODELSCOPE_CACHE=/root/autodl-tmp/models/modelscope ＃设置modelscope中的大模型保存路径
export LLAMAFACTORY_HOME=/root/autodl-tmp/LLaMA-Factory
3.准备数据
#在data/dataset_info.json中加入此数据
"docker_command_NL": {
"hf_hub_url": "MattCoddity/dockerNLcommands"
},
在data目录中加入训练数据，MattCoddity/dockerNLcommands.json
数据格式为：
[
{
"input": "Give me a list of containers that have the Ubuntu image as their ancestor.",
"instruction": "translate this sentence in docker command",
"output": "docker ps --filter 'ancestor=ubuntu'"
},
] 4.训练大模型
训练的参数文件：llama3_lora_sft_docker_command.yaml
### model
#md model id
model_name_or_path: LLM-Research/Meta-Llama-3-8B-Instruct
#huggingface model id
#model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
### method
stage: sft
do_train: true
finetuning_type: lora
lora_target: all
### dataset
dataset: docker_command_NL
template: llama3
cutoff_len: 1024
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16
### output
output_dir: /root/autodl-tmp/my-test/saves/llama3-8b/lora/sft/docker-commnad-nlp/sft
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
### train
per_device_train_batch_size: 4
gradient_accumulation_steps: 8
learning_rate: 1.0e-4
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 180000000
### eval
val_size: 0.1
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 500
训练命令：lora-train-docker-command.sh
BIN_PATH=$(cd `dirname $0`; pwd)
cd $BIN_PATH/
pwd
cd $LLAMAFACTORY_HOME
pwd
llamafactory-cli train $BIN_PATH/conf/llama3_lora_sft_docker_command.yaml
执行此命令即可开始训练大模型。
5.合并大模型
合并用的参数文件，llama3_lora_export_docker_command.yaml
### model
#md model id
model_name_or_path: LLM-Research/Meta-Llama-3-8B-Instruct
#huggingface model id
#model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
adapter_name_or_path: /root/autodl-tmp/my-test/saves/llama3-8b/lora/docker-commnad-nlp/sft
template: llama3
export_dir: /root/autodl-tmp/my-test/saves/llama3-8b/lora/docker-commnad-nlp/export
finetuning_type: lora
export_size: 2
export_device: gpu
export_legacy_format: False
合并命令，lora-export-docker-command.sh
BIN_PATH=$(cd `dirname $0`; pwd)
cd $BIN_PATH/
pwd
llamafactory-cli export conf/llama3_lora_export_docker_command.yaml
CONTROLNET是STABLE DIFFUSION中的一个插件，允许用户指定某张图片上的特征，然后将这些特征应用到新生成的图片上。
特征可以是图片上某人物的姿势，景深等。
其中一些实用的CONTROL TYPE：
1，LINER
STABLE DIFFUSION实现过程，其实就是先生成样图的线稿图，然后再上色。
2，TITLE
STABLE DIFFUSION会根据提供图片的骨架，再生成新的内容
3，SCRIBBLE
通常用于产品工业设计，先画出线稿，STABLE DIFFUSION会根据线稿，再根据提示词内容生成图片
采样步数越高，则画质超高。一般取值为20，高于20，画质和20的差不多。
采样一般就用EULER A这种。
提示如果不被模型认识，则不会起效果。
如果提示词太多，则排在后面的提示词会被忽略。
越靠前的词，越会被注意。
同类型的提示词之间会被污染。
反向提示词写几个就足够，如nsfw,low quality, lowres，写多反而会被忽略
一层小括号里面的提示词会加权重成1.1倍，两层则是1.21倍。
一层中括号里面的提示词会加权重成0.9倍，两层则是0.81倍。
[super man|iron man]则生成的主题会融合两种特征。
一键部署人工智能中的OPEN-WEBUI,OLLAMA, NGINX，也就对类似OPEN-AI的对话机器人
docker-compose.yaml
services:
# ollama:
# deploy:
# resources:
# reservations:
# devices:
# - driver: nvidia
# count: all
# capabilities:
# - gpu #使用GPU加速
# volumes:
# - ollama-volume:/root/.ollama #配置OLLAMA的配置数据文件在宿主机
# - /etc/localtime:/etc/localtime:ro
# container_name: ollama
# image: ollama/ollama
# restart: unless-stopped
# networks:
# - isolated #使用DOCKER的隔离网络
# - internet
vllm:
container_name: vllm
image: vllm/vllm-openai:latest
# ipc: host
volumes:
- ${HUGGINGFACE_MODELS_DIR}:/models
- /etc/localtime:/etc/localtime:ro
command: >
--model /models/models--unsloth--llama-3-8b-Instruct-lawdata
--served-model-name llama-3-8b-Instruct-lawdata
--gpu-memory-utilization 0.90
--max_model_len 1072
--quantization bitsandbytes
--load_format bitsandbytes
ports:
- "8000:8000"
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
networks:
- isolated #使用DOCKER的隔离网络
# https://github.com/open-webui/open-webui
open-webui: #全局维一的服务名
volumes:
- open-webui-volume:/app/backend/data #配置open-webui的配置数据文件在宿主机
- /etc/localtime:/etc/localtime:ro
container_name: open-webui
restart: unless-stopped
image: ghcr.io/open-webui/open-webui:main
# network_mode: host
ports:
- "3000:3000"
environment:
# - OLLAMA_BASE_URL=http://ollama:11434 #OPEN-WEBUI访问OLLAMA的地址，其实就是服务名代替IP
- ENABLE_OLLAMA_API=False
- OPENAI_API_BASE_URL=http://vllm:8000 /v1
- /etc/localtime:/etc/localtime:ro
- LOG_LEVEL=DEBUG
depends_on:
# - ollama
- vllm
networks:
- isolated
nginx-webui:
volumes:
- ${NGINX_DATA_DIR}/html:/usr/share/nginx/html:ro
- ${NGINX_DATA_DIR}/conf/nginx.conf:/etc/nginx/nginx.conf:ro
- ${NGINX_DATA_DIR}/conf/conf.d/default.conf:/etc/nginx/conf.d/default.conf:ro
- ${NGINX_DATA_DIR}/conf/.htpasswd:/etc/nginx/.htpasswd:ro
- /etc/localtime:/etc/localtime:ro
- ${NGINX_DATA_DIR}/log/access.log:/var/log/nginx/access.log
- ${NGINX_DATA_DIR}/log/error.log:/var/log/nginx/error.log
container_name: nginx-webui
ports:
- "81:81"
image: nginx:latest
#image: quay.io/ricardbejarano/nginx
depends_on:
- open-webui
restart: unless-stopped
networks:
- isolated
- internet
volumes:
ollama-volume:
driver: local
driver_opts:
type: none
o: bind
device: ${OLLAMA_DATA_DIR}
open-webui-volume:
driver: local
driver_opts:
type: none
o: bind
device: ${OPEN_WEBUI_DATA_DIR}
networks:
isolated:
driver: bridge
internal: true
internet:
driver: bridge
nginx.conf
user nginx;
worker_processes auto;
error_log /var/log/nginx/error.log warn;
pid /var/run/nginx.pid;
events {
worker_connections 1024;
}
http {
include /etc/nginx/mime.types;
default_type application/octet-stream;
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
'$status $body_bytes_sent "$http_referer" '
'"$http_user_agent" "$http_x_forwarded_for"';
access_log /var/log/nginx/access.log main;
sendfile on;
keepalive_timeout 65;
include /etc/nginx/conf.d/*.conf; # 加载 conf.d 目录下的配置文件
}
docker/docker-nginx/data/conf/conf.d/default.conf
# server {
# listen 80;
# server_name example.com www.example.com;
# root /usr/share/nginx/html;
# index index.html index.htm;
# location / {
# try_files $uri $uri/ =404;
# }
# error_page 500 502 503 504 /50x.html;
# location = /50x.html {
# root /usr/share/nginx/html;
# }
# }
server {
listen 81;
server_name localhost;
location / {
proxy_pass http://open-webui:8080;
# proxy_pass http://localhost:8080;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
}
# 代理 WebSocket 请求
location /ws/ {
proxy_pass http://open-webui:8080;
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "Upgrade";
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
}
access_log /var/log/nginx/access.log;
error_log /var/log/nginx/error.log;
}
00_varible.sh
#!/bin/bash
# 获取当前脚本的路径
# SCRIPT_PATH="$(realpath "$0")"
# echo "当前脚本的路径是: $SCRIPT_PATH"
# 获取当前脚本所在的目录
# SCRIPT_DIR="$(dirname "$SCRIPT_PATH")"
# echo "当前脚本所在的目录是: $SCRIPT_DIR"
# cd $SCRIPT_DIR
# export HTTP_PROXY=http://192.168.0.102:7890
# export HTTPS_PROXY=https://192.168.0.102:7890
export DOCKER_ROOT_DIR=/home/paul/paulwong/work/workspaces/python-ai-project/docker
export NGINX_DATA_DIR=${DOCKER_ROOT_DIR}/docker-nginx/data
export OLLAMA_DATA_DIR=${DOCKER_ROOT_DIR}/docker-ollama/data
export OPEN_WEBUI_DATA_DIR=${DOCKER_ROOT_DIR}/docker-webui/data
export HUGGINGFACE_MODELS_DIR=/home/paul/.cache/huggingface/models
01_start-nginx-ollama-webui.sh
#!/bin/bash
# 获取当前脚本的路径
SCRIPT_PATH="$(realpath "$0")"
echo "当前脚本的路径是: $SCRIPT_PATH"
# 获取当前脚本所在的目录
SCRIPT_DIR="$(dirname "$SCRIPT_PATH")"
echo "当前脚本所在的目录是: $SCRIPT_DIR"
cd $SCRIPT_DIR
source ./00_varible.sh
docker compose -f configs/docker-compose.yaml down
docker compose -f configs/docker-compose.yaml up
02_restart-nginx-ollama-webui.sh
#!/bin/bash
# 获取当前脚本的路径
SCRIPT_PATH="$(realpath "$0")"
echo "当前脚本的路径是: $SCRIPT_PATH"
# 获取当前脚本所在的目录
SCRIPT_DIR="$(dirname "$SCRIPT_PATH")"
echo "当前脚本所在的目录是: $SCRIPT_DIR"
cd $SCRIPT_DIR
source ./00_varible.sh
docker compose -f configs/docker-compose.yaml restart
03_login_ollama.sh
#!/bin/bash
# 获取当前脚本的路径
SCRIPT_PATH="$(realpath "$0")"
echo "当前脚本的路径是: $SCRIPT_PATH"
# 获取当前脚本所在的目录
SCRIPT_DIR="$(dirname "$SCRIPT_PATH")"
echo "当前脚本所在的目录是: $SCRIPT_DIR"
cd $SCRIPT_DIR
source ./00_varible.sh
docker compose -f configs/docker-compose.yaml exec ollama /bin/bash
# echo ${DOCKER_ROOT_DIR}
04_restart_open_webui.sh
#!/bin/bash
# 获取当前脚本的路径
SCRIPT_PATH="$(realpath "$0")"
echo "当前脚本的路径是: $SCRIPT_PATH"
# 获取当前脚本所在的目录
SCRIPT_DIR="$(dirname "$SCRIPT_PATH")"
echo "当前脚本所在的目录是: $SCRIPT_DIR"
cd $SCRIPT_DIR
source ./00_varible.sh
docker compose -f configs/docker-compose.yaml restart open-webui
# echo ${DOCKER_ROOT_DIR}