书生-进阶-第四关

一、部署

环境准备

conda create -n lmdeploy python=3.10 -y
conda activate lmdeploy
pip install lmdeploy==0.6.1 gradio==4.44.1 timm==1.0.9

下载源码

git clone https://github.com/Control-derek/InternVL2-Tutorial.git
cd InternVL2-Tutorial

运行

conda activate lmdeploy
python demo.py

效果图

识别错误，图片应该是新疆菜大盘鸡！下面微调解决！

二、微调

环境准备

conda create --name xtuner-env python=3.10 -y
conda activate xtuner-env

pip install xtuner==0.1.23 timm==1.0.9
pip install 'xtuner[deepspeed]'
pip install torch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 --index-url https://download.pytorch.org/whl/cu121
pip install transformers==4.39.0 peft==0.13.2

复制配置文件

cp /root/InternVL2-Tutorial/xtuner_config/internvl_v2_internlm2_2b_lora_finetune_food.py /root/xtuner/xtuner/configs/internvl/v2/internvl_v2_internlm2_2b_lora_finetune_food.py

微调

xtuner train /root/xtuner/xtuner/configs/internvl/v2/internvl_v2_internlm2_2b_lora_finetune_food.py --deepspeed deepspeed_zero2

转换格式

python xtuner/configs/internvl/v1_5/convert_to_official.py xtuner/configs/internvl/v2/internvl_v2_internlm2_2b_lora_finetune_food.py ./work_dirs/internvl_v2_internlm2_2b_lora_finetune_food/iter_640.pth ./work_dirs/internvl_v2_internlm2_2b_lora_finetune_food/lr35_ep10/

修改模型路径并运行微调后的模型

cd /root/InternVL2-Tutorial
conda activate lmdeploy
python demo.py

效果图

回答正确！