【基础岛第五关】书生大模型实战营 - XTuner 微调个人小助手认知

1. 构建环境

代码如下：

cd ~
#git clone 本repo
git clone https://github.com/InternLM/Tutorial.git -b camp4
mkdir -p /root/finetune && cd /root/finetune
conda create -n xtuner-env python=3.10 -y
conda activate xtuner-env

2. 安装XTuner 及 pytorch

代码如下：

cd /root/Tutorial/docs/L1/XTuner
pip install -r requirements.txt
pip install torch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 --index-url https://download.pytorch.org/whl/cu121

3. 验证XTuner是否正确安装

4. 数据准备

mkdir -p /root/finetune/data && cd /root/finetune/data
cp -r /root/Tutorial/data/assistant_Tuner.jsonl  /root/finetune/data

利用python来修改微调数据，在data目录下新建change_script.py文件，内容如下：

import json
import argparse
from tqdm import tqdm

def process_line(line, old_text, new_text):
    # 解析 JSON 行
    data = json.loads(line)
    
    # 递归函数来处理嵌套的字典和列表
    def replace_text(obj):
        if isinstance(obj, dict):
            return {k: replace_text(v) for k, v in obj.items()}
        elif isinstance(obj, list):
            return [replace_text(item) for item in obj]
        elif isinstance(obj, str):
            return obj.replace(old_text, new_text)
        else:
            return obj
    
    # 处理整个 JSON 对象
    processed_data = replace_text(data)
    
    # 将处理后的对象转回 JSON 字符串
    return json.dumps(processed_data, ensure_ascii=False)

def main(input_file, output_file, old_text, new_text):
    with open(input_file, 'r', encoding='utf-8') as infile, \
         open(output_file, 'w', encoding='utf-8') as outfile:
        
        # 计算总行数用于进度条
        total_lines = sum(1 for _ in infile)
        infile.seek(0)  # 重置文件指针到开头
        
        # 使用 tqdm 创建进度条
        for line in tqdm(infile, total=total_lines, desc="Processing"):
            processed_line = process_line(line.strip(), old_text, new_text)
            outfile.write(processed_line + '\n')

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Replace text in a JSONL file.")
    parser.add_argument("input_file", help="Input JSONL file to process")
    parser.add_argument("output_file", help="Output file for processed JSONL")
    parser.add_argument("--old_text", default="尖米", help="Text to be replaced")
    parser.add_argument("--new_text", default="大千", help="Text to replace with")
    args = parser.parse_args()

    main(args.input_file, args.output_file, args.old_text, args.new_text)

执行脚本：

cd ~/finetune/data
python change_script.py ./assistant_Tuner.jsonl ./assistant_Tuner_change.jsonl

5. 启动训练

做软连接，把InternStudio已经提供的模型连接到fineturne/models目录中

mkdir /root/finetune/models

ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2_5-7b-chat /root/finetune/models/internlm2_5-7b-chat

获取官方写好的 config

cd /root/finetune
mkdir ./config
cd config
xtuner copy-cfg internlm2_5_chat_7b_qlora_alpaca_e3 ./

修改配置文件，最终内容如下：

# Copyright (c) OpenMMLab. All rights reserved.
import torch
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, LinearLR
from peft import LoraConfig
from torch.optim import AdamW
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 alpaca_map_fn, template_map_fn_factory
from xtuner.engine.hooks import (DatasetInfoHook, EvaluateChatHook,
                                 VarlenAttnArgsToMessageHubHook)
from xtuner.engine.runner import TrainLoop
from xtuner.model import SupervisedFinetune
from xtuner.parallel.sequence import SequenceParallelSampler
from xtuner.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE

#######################################################################
#                          PART 1  Settings                           #
#######################################################################
# Model
pretrained_model_name_or_path = '/root/finetune/models/internlm2_5-7b-chat'
use_varlen_attn = False

# Data
alpaca_en_path = '/root/finetune/data/assistant_Tuner_change.jsonl'
prompt_template = PROMPT_TEMPLATE.internlm2_chat
max_length = 2048
pack_to_max_length = True

# parallel
sequence_parallel_size = 1

# Scheduler & Optimizer
batch_size = 1  # per_device
accumulative_counts = 1
accumulative_counts *= sequence_parallel_size
dataloader_num_workers = 0
max_epochs = 30
optim_type = AdamW
lr = 2e-4
betas = (0.9, 0.999)
weight_decay = 0
max_norm = 1  # grad clip
warmup_ratio = 0.03

# Save
save_steps = 10
save_total_limit = 2  # Maximum checkpoints to keep (-1 means unlimited)

# Evaluate the generation performance during the training
evaluation_freq = 10
SYSTEM = SYSTEM_TEMPLATE.alpaca
evaluation_inputs = [
    '请介绍一下你自己', 'Please introduce yourself'
]

#######################################################################
#                      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,
    use_varlen_attn=use_varlen_attn,
    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                   #
#######################################################################
alpaca_en = dict(
    type=process_hf_dataset,
    dataset=dict(type=load_dataset, path='json', data_files=dict(train=alpaca_en_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,
    use_varlen_attn=use_varlen_attn)

sampler = SequenceParallelSampler \
    if sequence_parallel_size > 1 else DefaultSampler
train_dataloader = dict(
    batch_size=batch_size,
    num_workers=dataloader_num_workers,
    dataset=alpaca_en,
    sampler=dict(type=sampler, shuffle=True),
    collate_fn=dict(type=default_collate_fn, use_varlen_attn=use_varlen_attn))

#######################################################################
#                    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=LinearLR,
        start_factor=1e-5,
        by_epoch=True,
        begin=0,
        end=warmup_ratio * max_epochs,
        convert_to_iter_based=True),
    dict(
        type=CosineAnnealingLR,
        eta_min=0.0,
        by_epoch=True,
        begin=warmup_ratio * max_epochs,
        end=max_epochs,
        convert_to_iter_based=True)
]

# train, val, test setting
train_cfg = dict(type=TrainLoop, max_epochs=max_epochs)

#######################################################################
#                           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)
]

if use_varlen_attn:
    custom_hooks += [dict(type=VarlenAttnArgsToMessageHubHook)]

# configure default hooks
default_hooks = dict(
    # record the time of every iteration.
    timer=dict(type=IterTimerHook),
    # print log every 10 iterations.
    logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=10),
    # enable the parameter scheduler.
    param_scheduler=dict(type=ParamSchedulerHook),
    # save checkpoint per `save_steps`.
    checkpoint=dict(
        type=CheckpointHook,
        by_epoch=False,
        interval=save_steps,
        max_keep_ckpts=save_total_limit),
    # set sampler seed in distributed evrionment.
    sampler_seed=dict(type=DistSamplerSeedHook),
)

# configure environment
env_cfg = dict(
    # whether to enable cudnn benchmark
    cudnn_benchmark=False,
    # set multi process parameters
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    # set distributed parameters
    dist_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)

# set log processor
log_processor = dict(by_epoch=False)

启动微调：

cd /root/finetune

xtuner train ./config/internlm2_5_chat_7b_qlora_alpaca_e3_copy.py --deepspeed deepspeed_zero2 --work-dir ./work_dirs/assistTuner

如果遇到如下错误：

安装 deepspeed==0.14.4 可以解决

pip install deepspeed==0.14.4

重新启动微调：

权重文件为使用Pytorch训练出来的，需要转换为HuggingFace格式。

转换命令：

# 先获取最后保存的一个pth文件
pth_file=`ls -t /root/finetune/work_dirs/assistTuner/*.pth | head -n 1 | sed 's/:$//'`
export MKL_SERVICE_FORCE_INTEL=1
export MKL_THREADING_LAYER=GNU
xtuner convert pth_to_hf ./internlm2_5_chat_7b_qlora_alpaca_e3_copy.py ${pth_file} ./hf

转换之后的文件：

6. 模型合并

转换为之后并不是一个完整的模型，还需要把该权重与基座模型进行合并，合并之后才是一个完整的模型，就可以被直接使用了。

XTuner的合并命令为 xtuner convert merge。

xtuner convert merge /root/finetune/models/internlm2_5-7b-chat ./hf ./merged --max-shard-size 2GB

合并之后的目录结构：

7. 利用合并模型 web 对话

修改/root/Tutorial/tools/L1_XTuner_code/xtuner_streamlit_demo.py文件，把其中的模型修改为我们刚刚合并的模型路径，然后执行。

 利用端口映射把服务器中的8501端口映射到本地

ssh -CNg -L 8501:127.0.0.1:8501 root@ssh.intern-ai.org.cn

 浏览器访问 127.0.0.1:8501, 效果如下：