4、XTuner微调个人小助手（homework）

基础作业（结营必做）

训练自己的小助手认知（记录复现过程并截图）

1，环境安装

# 如果你是在 InternStudio 平台，则从本地 clone 一个已有 pytorch 的环境：
# pytorch    2.0.1   py3.10_cuda11.7_cudnn8.5.0_0

studio-conda xtuner0.1.17
# 如果你是在其他平台：
# conda create --name xtuner0.1.17 python=3.10 -y

# 激活环境
conda activate xtuner0.1.17
# 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
mkdir -p /root/xtuner0117 && cd /root/xtuner0117

# 拉取 0.1.17 的版本源码
git clone -b v0.1.17  https://github.com/InternLM/xtuner
# 无法访问github的用户请从 gitee 拉取:
# git clone -b v0.1.15 https://gitee.com/Internlm/xtuner

# 进入源码目录
cd /root/xtuner0117/xtuner

# 从源码安装 XTuner
pip install -e '.[all]'

2、数据准备

# 创建 `generate_data.py` 文件
touch /root/ft/data/generate_data.py

import json

# 设置用户的名字
name = 'Eagle102'
# 设置需要重复添加的数据次数
n =  10000

# 初始化OpenAI格式的数据结构
data = [
    {
        "messages": [
            {
                "role": "user",
                "content": "请做一下自我介绍"
            },
            {
                "role": "assistant",
                "content": "我是{}的小助手，内在是上海AI实验室书生·浦语的1.8B大模型哦".format(name)
            }
        ]
    }
]

# 通过循环，将初始化的对话数据重复添加到data列表中
for i in range(n):
    data.append(data[0])

# 将data列表中的数据写入到一个名为'personal_assistant.json'的文件中
with open('personal_assistant.json', 'w', encoding='utf-8') as f:
    # 使用json.dump方法将数据以JSON格式写入文件
    # ensure_ascii=False 确保中文字符正常显示
    # indent=4 使得文件内容格式化，便于阅读
    json.dump(data, f, ensure_ascii=False, indent=4)

# 确保先进入该文件夹
cd /root/ft/data

# 运行代码
python /root/ft/data/generate_data.py

3、模型准备

# 创建符号链接
ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b /root/xtuner0117/ft/model


# 配置文件选择
xtuner list-cfg -p internlm2_1_8b

# 创建一个存放 config 文件的文件夹
mkdir -p /root/xtuner0117/ft/config

# 使用 XTuner 中的 copy-cfg 功能将 config 文件复制到指定的位置
xtuner copy-cfg internlm2_1_8b_qlora_alpaca_e3 /root/xtuner0117/ft/config

4、配置文件修改

修改，internlm2_1_8b_qlora_alpaca_e3_copy.py

# 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 openai_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/xtuner0117/ft/model'
use_varlen_attn = False

# Data
alpaca_en_path = '/root/xtuner0117/ft/data/personal_assistant.json'
prompt_template = PROMPT_TEMPLATE.default
max_length = 1024
pack_to_max_length = True

# parallel
sequence_parallel_size = 1

# Scheduler & Optimizer
batch_size = 1  # per_device
accumulative_counts = 16
accumulative_counts *= sequence_parallel_size
dataloader_num_workers = 0
max_epochs = 2
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 = 300
save_total_limit = 3  # Maximum checkpoints to keep (-1 means unlimited)

# Evaluate the generation performance during the training
evaluation_freq = 300
SYSTEM = ''
evaluation_inputs = ['请你介绍一下你自己', '你是谁', '你是我的小助手吗']

#######################################################################
#                      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=openai_map_fn,
    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)

5、模型训练

# 使用 deepspeed 来加速训练
xtuner train /root/xtuner0117/ft/config/internlm2_1_8b_qlora_alpaca_e3_copy.py --work-dir /root/xtuner0117/ft/train_deepspeed --deepspeed deepspeed_zero2

6、训练过程

进阶作业

将自我认知的模型上传到 OpenXLab，并将应用部署到 OpenXLab（优秀学员必做）

1、将模型转化成huggingface

# 创建一个保存转换后 Huggingface 格式的文件夹
mkdir -p /root/ft/huggingface

# 模型转换
# xtuner convert pth_to_hf ${配置文件地址} ${权重文件地址} ${转换后模型保存地址}
xtuner convert pth_to_hf /root/ft/train/internlm2_1_8b_qlora_alpaca_e3_copy.py /root/ft/train/iter_768.pth /root/ft/huggingface

# 创建一个名为 final_model 的文件夹存储整合后的模型文件
mkdir -p /root/ft/final_model

# 解决一下线程冲突的 Bug 
export MKL_SERVICE_FORCE_INTEL=1

# 进行模型整合
# xtuner convert merge  ${NAME_OR_PATH_TO_LLM} ${NAME_OR_PATH_TO_ADAPTER} ${SAVE_PATH} 
xtuner convert merge /root/ft/model /root/ft/huggingface /root/ft/final_model

2、模型上传到X

git lfs track "*.bin"
git lfs track "*.model"

cd finel_model
git add -A
git commit -m "upload model"
git push

3、部署

复现多模态微调（优秀学员必做）

1、创建配置文件

# 查询xtuner内置配置文件
xtuner list-cfg -p llava_internlm2_chat_1_8b

# 拷贝配置文件到当前目录
xtuner copy-cfg \
  llava_internlm2_chat_1_8b_qlora_clip_vit_large_p14_336_lora_e1_gpu8_finetune \
  /root/tutorial/xtuner/llava

修改配置文件：

# Copyright (c) OpenMMLab. All rights reserved.
import torch
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, CLIPImageProcessor,
                          CLIPVisionModel)

from xtuner.dataset import LLaVADataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.map_fns import llava_map_fn, template_map_fn_factory
from xtuner.dataset.samplers import LengthGroupedSampler
from xtuner.engine.hooks import DatasetInfoHook, EvaluateChatHook
from xtuner.engine.runner import TrainLoop
from xtuner.model import LLaVAModel
from xtuner.utils import PROMPT_TEMPLATE

#######################################################################
#                          PART 1  Settings                           #
#######################################################################
# Model
llm_name_or_path = '/root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b'
visual_encoder_name_or_path = '/root/share/new_models/openai/clip-vit-large-patch14-336'
# Specify the pretrained pth
pretrained_pth = '/root/share/new_models/xtuner/iter_2181.pth'  # noqa: E501

# Data
data_root = '/root/tutorial/xtuner/llava/llava_data/'
data_path = data_root + 'repeated_data.json'
image_folder = data_root 
prompt_template = PROMPT_TEMPLATE.internlm2_chat
max_length = int(2048 - (336 / 14)**2)

# Scheduler & Optimizer
batch_size = 1  # per_device
accumulative_counts = 1
dataloader_num_workers = 0
max_epochs = 1
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 = 500
save_total_limit = 2  # Maximum checkpoints to keep (-1 means unlimited)

# Evaluate the generation performance during the training
evaluation_freq = 500
SYSTEM = ''
evaluation_images = 'https://llava-vl.github.io/static/images/view.jpg'
# evaluation_inputs = ['请描述一下这张照片', 'Please describe this picture']
evaluation_inputs = ['Please describe this picture','What is the equipment in the image?']

#######################################################################
#            PART 2  Model & Tokenizer & Image Processor              #
#######################################################################
tokenizer = dict(
    type=AutoTokenizer.from_pretrained,
    pretrained_model_name_or_path=llm_name_or_path,
    trust_remote_code=True,
    padding_side='right')

image_processor = dict(
    type=CLIPImageProcessor.from_pretrained,
    pretrained_model_name_or_path=visual_encoder_name_or_path,
    trust_remote_code=True)

model = dict(
    type=LLaVAModel,
    freeze_llm=True,
    freeze_visual_encoder=True,
    pretrained_pth=pretrained_pth,
    llm=dict(
        type=AutoModelForCausalLM.from_pretrained,
        pretrained_model_name_or_path=llm_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')),
    llm_lora=dict(
        type=LoraConfig,
        r=512,
        lora_alpha=256,
        lora_dropout=0.05,
        bias='none',
        task_type='CAUSAL_LM'),
    visual_encoder=dict(
        type=CLIPVisionModel.from_pretrained,
        pretrained_model_name_or_path=visual_encoder_name_or_path),
    visual_encoder_lora=dict(
        type=LoraConfig, r=64, lora_alpha=16, lora_dropout=0.05, bias='none'))

#######################################################################
#                      PART 3  Dataset & Dataloader                   #
#######################################################################
llava_dataset = dict(
    type=LLaVADataset,
    data_path=data_path,
    image_folder=image_folder,
    tokenizer=tokenizer,
    image_processor=image_processor,
    dataset_map_fn=llava_map_fn,
    template_map_fn=dict(
        type=template_map_fn_factory, template=prompt_template),
    max_length=max_length,
    pad_image_to_square=True)

train_dataloader = dict(
    batch_size=batch_size,
    num_workers=dataloader_num_workers,
    dataset=llava_dataset,
    sampler=dict(
        type=LengthGroupedSampler,
        length_property='modality_length',
        per_device_batch_size=batch_size * accumulative_counts),
    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=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,
        image_processor=image_processor,
        every_n_iters=evaluation_freq,
        evaluation_inputs=evaluation_inputs,
        evaluation_images=evaluation_images,
        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 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)

2、开始Finetune

cd /root/tutorial/xtuner/llava/
xtuner train /root/tutorial/xtuner/llava/llava_internlm2_chat_1_8b_qlora_clip_vit_large_p14_336_lora_e1_gpu8_finetune_copy.py --deepspeed deepspeed_zero2