书生第四期L1G5000 XTuner 微调实践微调

使用 conda 先构建一个 Python-3.10 的虚拟环境

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

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

验证安装

xtuner list-cfg

创建一个新的文件夹用于存储微调数据

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

创建修改脚本

# 创建 `change_script.py` 文件
touch /root/finetune/data/change_script.py

打开change_script.py文件后将下面的内容复制进去

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="自己的名字", 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

# usage：python change_script.py {input_file.jsonl} {output_file.jsonl}
cd ~/finetune/data
python change_script.py ./assistant_Tuner.jsonl ./assistant_Tuner_change.jsonl

查看数据

cat assistant_Tuner_change.jsonl | head -n 3

复制模型

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

修改 Config

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

修改以下几行 

#######################################################################
#                          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)

启动微调：

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

权重转换

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
xtuner convert pth_to_hf ./internlm2_5_chat_7b_qlora_alpaca_e3_copy.py ${pth_file} ./hf

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

 模型 WebUI 对话

cd ~/Tutorial/tools/L1_XTuner_code
 
# 直接修改脚本文件第18行
- model_name_or_path = "Shanghai_AI_Laboratory/internlm2_5-7b-chat"
+ model_name_or_path = "/root/finetune/work_dirs/assistTuner/merged"
 
conda activate xtuner-env
 
streamlit run /root/Tutorial/tools/L1_XTuner_code/xtuner_streamlit_demo.py
 
ssh -CNg -L 8501:127.0.0.1:8501 root@ssh.intern-ai.org.cn -p *****