XTuner InternLM-Chat 个人小助手认知微调实践
1.概述
目标：通过微调，帮助模型了解对自己身份
方式：使用XTuner进行微调
2.实操
2.1微调环境准备
参考：
XTuner复现-CSDN博客
# InternStudio 平台中，从本地 clone 一个已有 pytorch 2.0.1 的环境（后续均在该环境执行，若为其他环境可作为参考）
# 进入环境后首先 bash
# 进入环境后首先 bash
# 进入环境后首先 bash
bash
conda create --name personal_assistant --clone=/root/share/conda_envs/internlm-base
# 如果在其他平台：
# conda create --name personal_assistant python=3.10 -y# 激活环境
conda activate personal_assistant
# 进入家目录 （~的意思是 “当前用户的home路径”）
cd ~
# 创建版本文件夹并进入，以跟随本教程
# personal_assistant用于存放本教程所使用的东西
mkdir /root/personal_assistant && cd /root/personal_assistant
mkdir /root/personal_assistant/xtuner019 && cd /root/personal_assistant/xtuner019# 拉取 0.1.9 的版本源码
git clone -b v0.1.9 https://github.com/InternLM/xtuner
# 无法访问github的用户请从 gitee 拉取:
# git clone -b v0.1.9 https://gitee.com/Internlm/xtuner# 进入源码目录
cd xtuner# 从源码安装 XTuner
pip install -e '.[all]'2.2数据准备
创建data文件夹用于存放用于训练的数据集
mkdir -p /root/personal_assistant/data && cd /root/personal_assistant/data在data目录下创建一个json文件personal_assistant.json作为本次微调所使用的数据集。json中内容可参考下方(复制粘贴n次做数据增广，数据量小无法有效微调，下面仅用于展示格式，下面也有生成脚本)
其中conversation表示一次对话的内容，input为输入，即用户会问的问题，output为输出，即想要模型回答的答案。
以下是一个python脚本，用于生成数据集。在data目录下新建一个generate_data.py文件，将以下代码复制进去，然后运行该脚本即可生成数据集。
2.3配置准备
下载模型InternLM-chat-7B
InternStudio 平台的 share 目录下已经为我们准备了全系列的 InternLM 模型，可以使用如下命令复制internlm-chat-7b：
mkdir -p /root/personal_assistant/model/Shanghai_AI_Laboratory
cp -r /root/share/temp/model_repos/internlm-chat-7b /root/personal_assistant/model/Shanghai_AI_LaboratoryXTuner 提供多个开箱即用的配置文件，用户可以通过下列命令查看：
# 列出所有内置配置
xtuner list-cfg#创建用于存放配置的文件夹config并进入
mkdir /root/personal_assistant/config && cd /root/personal_assistant/config
拷贝一个配置文件到当前目录：xtuner copy-cfg ${CONFIG_NAME} ${SAVE_PATH} 在本例中：（注意最后有个英文句号，代表复制到当前路径）
xtuner copy-cfg internlm_chat_7b_qlora_oasst1_e3 .修改拷贝后的文件internlm_chat_7b_qlora_oasst1_e3_copy.py，在原文修改
# PART 1 中
# 预训练模型存放的位置
pretrained_model_name_or_path = '/root/personal_assistant/model/Shanghai_AI_Laboratory/internlm-chat-7b'# 微调数据存放的位置
data_path = '/root/personal_assistant/data/personal_assistant.json'# 训练中最大的文本长度
max_length = 512# 每一批训练样本的大小
batch_size = 2# 最大训练轮数
max_epochs = 3# 验证的频率
evaluation_freq = 90# 用于评估输出内容的问题（用于评估的问题尽量与数据集的question保持一致）
evaluation_inputs = [ '请介绍一下你自己', '请做一下自我介绍' ]# PART 3 中
dataset=dict(type=load_dataset, path='json', data_files=dict(train=data_path))
dataset_map_fn=None修改后代码为
# Copyright (c) OpenMMLab. All rights reserved.
import torch
from bitsandbytes.optim import PagedAdamW32bit
from datasets import load_dataset
from mmengine.dataset import DefaultSampler
from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook,LoggerHook, ParamSchedulerHook)
from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR
from peft import LoraConfig
from transformers import (AutoModelForCausalLM, AutoTokenizer,BitsAndBytesConfig)from xtuner.dataset import process_hf_dataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.map_fns import oasst1_map_fn, template_map_fn_factory
from xtuner.engine import DatasetInfoHook, EvaluateChatHook
from xtuner.model import SupervisedFinetune
from xtuner.utils import PROMPT_TEMPLATE#######################################################################
# PART 1 Settings #
#######################################################################
# Model
pretrained_model_name_or_path = '/root/personal_assistant/model/Shanghai_AI_Laboratory/internlm-chat-7b'# Data
data_path = '/root/personal_assistant/data/personal_assistant.json'
prompt_template = PROMPT_TEMPLATE.internlm_chat
max_length = 512
pack_to_max_length = True# Scheduler & Optimizer
batch_size = 2 # per_device
accumulative_counts = 16
dataloader_num_workers = 0
max_epochs = 3
optim_type = PagedAdamW32bit
lr = 2e-4
betas = (0.9, 0.999)
weight_decay = 0
max_norm = 1 # grad clip# Evaluate the generation performance during the training
evaluation_freq = 90
SYSTEM = ''
evaluation_inputs = [ '请介绍一下你自己', '请做一下自我介绍' ]#######################################################################
# PART 2 Model & Tokenizer #
#######################################################################
tokenizer = dict(type=AutoTokenizer.from_pretrained,pretrained_model_name_or_path=pretrained_model_name_or_path,trust_remote_code=True,padding_side='right')model = dict(type=SupervisedFinetune,llm=dict(type=AutoModelForCausalLM.from_pretrained,pretrained_model_name_or_path=pretrained_model_name_or_path,trust_remote_code=True,torch_dtype=torch.float16,quantization_config=dict(type=BitsAndBytesConfig,load_in_4bit=True,load_in_8bit=False,llm_int8_threshold=6.0,llm_int8_has_fp16_weight=False,bnb_4bit_compute_dtype=torch.float16,bnb_4bit_use_double_quant=True,bnb_4bit_quant_type='nf4')),lora=dict(type=LoraConfig,r=64,lora_alpha=16,lora_dropout=0.1,bias='none',task_type='CAUSAL_LM'))#######################################################################
# PART 3 Dataset & Dataloader #
#######################################################################
train_dataset = dict(type=process_hf_dataset,dataset=dict(type=load_dataset, path='json', data_files=dict(train=data_path)),tokenizer=tokenizer,max_length=max_length,dataset_map_fn=None,template_map_fn=dict(type=template_map_fn_factory, template=prompt_template),remove_unused_columns=True,shuffle_before_pack=True,pack_to_max_length=pack_to_max_length)train_dataloader = dict(batch_size=batch_size,num_workers=dataloader_num_workers,dataset=train_dataset,sampler=dict(type=DefaultSampler, shuffle=True),collate_fn=dict(type=default_collate_fn))#######################################################################
# PART 4 Scheduler & Optimizer #
#######################################################################
# optimizer
optim_wrapper = dict(type=AmpOptimWrapper,optimizer=dict(type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay),clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False),accumulative_counts=accumulative_counts,loss_scale='dynamic',dtype='float16')# learning policy
# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501
param_scheduler = dict(type=CosineAnnealingLR,eta_min=0.0,by_epoch=True,T_max=max_epochs,convert_to_iter_based=True)# train, val, test setting
train_cfg = dict(by_epoch=True, max_epochs=max_epochs, val_interval=1)#######################################################################
# PART 5 Runtime #
#######################################################################
# Log the dialogue periodically during the training process, optional
custom_hooks = [dict(type=DatasetInfoHook, tokenizer=tokenizer),dict(type=EvaluateChatHook,tokenizer=tokenizer,every_n_iters=evaluation_freq,evaluation_inputs=evaluation_inputs,system=SYSTEM,prompt_template=prompt_template)
]# configure default hooks
default_hooks = dict(# record the time of every iteration.timer=dict(type=IterTimerHook),# print log every 100 iterations.logger=dict(type=LoggerHook, interval=10),# enable the parameter scheduler.param_scheduler=dict(type=ParamSchedulerHook),# save checkpoint per epoch.checkpoint=dict(type=CheckpointHook, interval=1),# set sampler seed in distributed evrionment.sampler_seed=dict(type=DistSamplerSeedHook),
)# configure environment
env_cfg = dict(# whether to enable cudnn benchmarkcudnn_benchmark=False,# set multi process parametersmp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),# set distributed parametersdist_cfg=dict(backend='nccl'),
)# set visualizer
visualizer = None# set log level
log_level = 'INFO'# load from which checkpoint
load_from = None# whether to resume training from the loaded checkpoint
resume = False# Defaults to use random seed and disable `deterministic`
randomness = dict(seed=None, deterministic=False)
2.4微调启动
用xtuner train命令启动训练
xtuner train /root/personal_assistant/config/internlm_chat_7b_qlora_oasst1_e3_copy.py
5微调后参数转换/合并
训练后的pth格式参数转Hugging Face格式
# 创建用于存放Hugging Face格式参数的hf文件夹
cd /root/personal_assistant/config/
mkdir work_dirs
cd work_dirs
mkdir hfexport MKL_SERVICE_FORCE_INTEL=1# 配置文件存放的位置
export CONFIG_NAME_OR_PATH=/root/personal_assistant/config/internlm_chat_7b_qlora_oasst1_e3_copy.py# 模型训练后得到的pth格式参数存放的位置
export PTH=/root/personal_assistant/work_dirs/internlm_chat_7b_qlora_oasst1_e3_copy/epoch_3.pth# pth文件转换为Hugging Face格式后参数存放的位置
export SAVE_PATH=/root/personal_assistant/config/work_dirs/hf# 执行参数转换
xtuner convert pth_to_hf $CONFIG_NAME_OR_PATH $PTH $SAVE_PATH
Merge模型参数
export MKL_SERVICE_FORCE_INTEL=1
export MKL_THREADING_LAYER='GNU'# 原始模型参数存放的位置
export NAME_OR_PATH_TO_LLM=/root/personal_assistant/model/Shanghai_AI_Laboratory/internlm-chat-7b# Hugging Face格式参数存放的位置
export NAME_OR_PATH_TO_ADAPTER=/root/personal_assistant/config/work_dirs/hf# 最终Merge后的参数存放的位置
mkdir /root/personal_assistant/config/work_dirs/hf_merge
export SAVE_PATH=/root/personal_assistant/config/work_dirs/hf_merge# 执行参数Merge
xtuner convert merge \$NAME_OR_PATH_TO_LLM \$NAME_OR_PATH_TO_ADAPTER \$SAVE_PATH \--max-shard-size 2GB
2.6网页DEMO
安装网页Demo所需依赖
pip install streamlit==1.24.0
下载InternLM项目代码
# 创建code文件夹用于存放InternLM项目代码
mkdir /root/personal_assistant/code && cd /root/personal_assistant/code
git clone https://github.com/InternLM/InternLM.git将 /root/code/InternLM/web_demo.py 中 29 行和 33 行的模型路径更换为Merge后存放参数的路径 /root/personal_assistant/config/work_dirs/hf_merge
运行 /root/personal_assistant/code/InternLM 目录下的 web_demo.py 文件，输入以下命令后，(端口映射请参考：轻松玩转书生·浦语大模型internlm-demo 配置验证过程_ssh -cng -l 7860:127.0.0.1:6006 root@ssh.intern-ai-CSDN博客)，将端口映射到本地。在本地浏览器输入 http://127.0.0.1:6006 即可。（图片路径没搞好）
streamlit run /root/personal_assistant/code/InternLM/web_demo.py --server.address 127.0.0.1 --server.port 6006