进阶岛第4关：InternVL 多模态模型部署微调实践

准备InternVL模型

我们使用InternVL2-2B模型。该模型已在share文件夹下挂载好，现在让我们把移动出来。

mkdir -p /root/project/joke/model
cp -r /root/share/new_models/OpenGVLab/InternVL2-2B /root/project/joke/model

# 不用ln -s

准备环境

这里我们来手动配置下xtuner。

conda create --name xtuner python=3.10 -y# 激活虚拟环境（注意：后续的所有操作都需要在这个虚拟环境中进行）
conda activate xtuner# 安装一些必要的库
conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia -y
# 安装其他依赖
apt install libaio-dev
pip install transformers==4.39.3
pip install streamlit==1.36.0cd /root/project/joke/codegit clone -b v0.1.23  https://github.com/InternLM/XTunercd XTuner
pip install -e '.[deepspeed]'pip install lmdeploy==0.5.3 datasets matplotlib Pillow timmxtuner version

准备微调数据集

我们这里使用huggingface上的zhongshsh/CLoT-Oogiri-GO据集，特别鸣谢～。

数据集我们从官网下载下来并进行去重，只保留中文数据等操作。并制作成XTuner需要的形式。并已在share里，我们一起从share里挪出数据集。

## 首先让我们安装一下需要的包
pip install datasets matplotlib Pillow timm## 让我们把数据集挪出来
cp -r /root/share/new_models/datasets/CLoT_cn_2000 /root/InternLM/datasets/

让我们打开数据集的一张图看看，我们选择jsonl里的第一条数据对应的图片。首先我们先把这张图片挪动到InternLM文件夹下面。

cp InternLM/datasets/CLoT_cn_2000/ex_images/007aPnLRgy1hb39z0im50j30ci0el0wm.jpg InternLM/

InternVL 推理部署攻略

使用pipeline进行推理

之后我们使用lmdeploy自带的pipeline工具进行开箱即用的推理流程，首先我们新建一个文件。

touch /root/InternLM/code/test_lmdeploy.py
cd /root/InternLM/code/

然后把以下代码拷贝进test_lmdeploy.py中。

from lmdeploy import pipeline
from lmdeploy.vl import load_imagepipe = pipeline('/root/model/InternVL2-2B')image = load_image('/root/InternLM/007aPnLRgy1hb39z0im50j30ci0el0wm.jpg')
response = pipe(('请你根据这张图片，讲一个脑洞大开的梗', image))
print(response.text)

运行执行推理结果。

python3 test_lmdeploy.py

推理后我们发现直接使用2b模型不能很好的讲出梗，现在我们要对这个2b模型进行微调。

配置微调参数

让我们一起修改XTuner下 InternVL的config，文件在： /root/InternLM/code/XTuner/xtuner/configs/internvl/v2/internvl_v2_internlm2_2b_qlora_finetune.py

总体config文件(复制即可)

# Copyright (c) OpenMMLab. All rights reserved.
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 AutoTokenizerfrom xtuner.dataset import InternVL_V1_5_Dataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.samplers import LengthGroupedSampler
from xtuner.engine.hooks import DatasetInfoHook
from xtuner.engine.runner import TrainLoop
from xtuner.model import InternVL_V1_5
from xtuner.utils import PROMPT_TEMPLATE#######################################################################
#                          PART 1  Settings                           #
#######################################################################
# Model
path = '/root/model/InternVL2-2B'# Data
data_root = '/root/InternLM/datasets/CLoT_cn_2000/'
data_path = data_root + 'ex_cn.json'
image_folder = data_root
prompt_template = PROMPT_TEMPLATE.internlm2_chat
max_length = 6656# Scheduler & Optimizer
batch_size = 4  # per_device
accumulative_counts = 4
dataloader_num_workers = 4
max_epochs = 6
optim_type = AdamW
# official 1024 -> 4e-5
lr = 2e-5
betas = (0.9, 0.999)
weight_decay = 0.05
max_norm = 1  # grad clip
warmup_ratio = 0.03# Save
save_steps = 1000
save_total_limit = 1  # Maximum checkpoints to keep (-1 means unlimited)#######################################################################
#            PART 2  Model & Tokenizer & Image Processor              #
#######################################################################
model = dict(type=InternVL_V1_5,model_path=path,freeze_llm=True,freeze_visual_encoder=True,quantization_llm=True,  # or Falsequantization_vit=False,  # or True and uncomment visual_encoder_lora# comment the following lines if you don't want to use Lora in llmllm_lora=dict(type=LoraConfig,r=128,lora_alpha=256,lora_dropout=0.05,target_modules=None,task_type='CAUSAL_LM'),# uncomment the following lines if you don't want to use Lora in visual encoder # noqa# visual_encoder_lora=dict(#     type=LoraConfig, r=64, lora_alpha=16, lora_dropout=0.05,#     target_modules=['attn.qkv', 'attn.proj', 'mlp.fc1', 'mlp.fc2'])
)#######################################################################
#                      PART 3  Dataset & Dataloader                   #
#######################################################################
llava_dataset = dict(type=InternVL_V1_5_Dataset,model_path=path,data_paths=data_path,image_folders=image_folder,template=prompt_template,max_length=max_length)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
tokenizer = dict(type=AutoTokenizer.from_pretrained,pretrained_model_name_or_path=path,trust_remote_code=True)custom_hooks = [dict(type=DatasetInfoHook, tokenizer=tokenizer),
]# 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,save_optimizer=False,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 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)# set log processor
log_processor = dict(by_epoch=False)

开始训练

这里使用之前搞好的configs进行训练。咱们要调整一下batch size，并且使用qlora。要不半卡不够用的 QAQ。

cd XTuner

NPROC_PER_NODE=1 xtuner train /root/InternLM/code/XTuner/xtuner/configs/internvl/v2/internvl_v2_internlm2_2b_qlora_finetune.py --work-dir /root/InternLM/work_dir/internvl_ft_run_8_filter --deepspeed deepspeed_zero1

合并权重&&模型转换

用官方脚本进行权重合并

cd XTuner
# transfer weights
python3 xtuner/configs/internvl/v1_5/convert_to_official.py xtuner/configs/internvl/v2/internvl_v2_internlm2_2b_qlora_finetune.py /root/InternLM/work_dir/internvl_ft_run_8_filter/iter_3000.pth /root/InternLM/InternVL2-2B/

最后我们的模型在：/root/InternLM/convert_model/，文件格式：

微调后效果对比

现在我们微调好啦，让我们再来试试这张图片吧！

from lmdeploy import pipeline
from lmdeploy.vl import load_imagepipe = pipeline('/root/InternLM/InternVL2-2B')image = load_image('/root/InternLM/007aPnLRgy1hb39z0im50j30ci0el0wm.jpg')
response = pipe(('请你根据这张图片，讲一个脑洞大开的梗', image))
print(response.text)