书生-基础-第五关

一、安装XTuner

git clone https://github.com/InternLM/xtuner.git
cd /root/finetune/xtuner

pip install  -e '.[all]'
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

二、配置Config

获取对应的config文件

# cd {path/to/finetune}
cd /root/finetune
mkdir ./config
cd config
xtuner copy-cfg internlm2_5_chat_7b_qlora_alpaca_e3 ./

修改部分配置

#######################################################################
#                          PART 1  Settings                           #
#######################################################################
- pretrained_model_name_or_path = 'internlm/internlm2_5-7b-chat'
+ pretrained_model_name_or_path = '/root/finetune/models/internlm2_5-7b-chat'

- alpaca_en_path = 'tatsu-lab/alpaca'
+ alpaca_en_path = '/root/finetune/data/assistant_Tuner_change.jsonl'


evaluation_inputs = [
-    '请给我介绍五个上海的景点', 'Please tell me five scenic spots in Shanghai'
+    '请介绍一下你自己', 'Please introduce yourself'
]

#######################################################################
#                      PART 3  Dataset & Dataloader                   #
#######################################################################
alpaca_en = dict(
    type=process_hf_dataset,
-   dataset=dict(type=load_dataset, path=alpaca_en_path),
+   dataset=dict(type=load_dataset, path='json', data_files=dict(train=alpaca_en_path)),
    tokenizer=tokenizer,
    max_length=max_length,
-   dataset_map_fn=alpaca_map_fn,
+   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)

三、微调

cd /root/finetune
conda activate xtuner-env

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

四、权重转换

将原本使用 Pytorch 训练出来的模型权重文件转换为目前通用的 HuggingFace 格式文件

cd /root/finetune/work_dirs/assistTuner

conda activate xtuner-env

# 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`
export MKL_SERVICE_FORCE_INTEL=1
export MKL_THREADING_LAYER=GNU
# 将"${pth_file}"替换为实际路径，否则可能会报路径不存在的问题
xtuner convert pth_to_hf ./internlm2_5_chat_7b_qlora_alpaca_e3_copy.py ${pth_file} ./hf

五、模型合并

cd /root/finetune/work_dirs/assistTuner
conda activate xtuner-env

export MKL_SERVICE_FORCE_INTEL=1
export MKL_THREADING_LAYER=GNU
xtuner convert merge /root/finetune/models/internlm2_5-7b-chat ./hf ./merged --max-shard-size 2GB

六、合并后的模型目录

七、运行