【书生·浦语大模型实战营】第4节：XTuner（笔记及作业）

【书生·浦语大模型实战营】第4节：XTuner

视频与文档地址

视频：https://www.bilibili.com/video/BV15m421j78d/?spm_id_from=333.1007.top_right_bar_window_custom_collection.content.click&vd_source=724260feabc8c4fa14ba533aaff72464

文档：Tutorial/xtuner/personal_assistant_document.md at camp2 · InternLM/Tutorial (github.com)

视频主要介绍了LLM在下游训练时常用的微调方式，包括全量微调、lora、qlora等

以及Xtuner能实现对多种LLM的微调

作业

环境配置

studio-conda xtuner0.1.17

conda activate xtuner0.1.17

cd ~

mkdir -p /root/xtuner0117 && cd /root/xtuner0117

git clone -b v0.1.17  https://github.com/InternLM/xtuner

cd /root/xtuner0117/xtuner

pip install -e '.[all]'

数据集准备

mkdir -p /root/ft && cd /root/ft

mkdir -p /root/ft/data && cd /root/ft/data

touch /root/ft/data/generate_data.py

修改内容

import json

# 设置用户的名字
name = '大蟑螂'
# 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，爱好是抓癞蛤蟆吓老头".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)

运行文件

cd /root/ft/data

python /root/ft/data/generate_data.py

获得.json文件用于后续模型微调

模型准备

拉取模型到本地

使用xtuner list-cfg指令获取xtuner支持的模型及对应的微调方式

xtuner list-cfg -p model 指令可获得指定模型的配置文件名

mkdir -p /root/ft/config

xtuner copy-cfg internlm2_1_8b_qlora_alpaca_e3 /root/ft/config # 将xtuner中的配置文件存放到本地

查看配置文件并基于需求对配置文件进行修改，包括修改模型地址为本地模型地址、数据集地址等

模型微调训练

模型训练，支持常规训练和使用deepspeed加速训练

xtuner train /root/ft/config/internlm2_1_8b_qlora_alpaca_e3_copy.py --work-dir /root/ft/train # 常规

xtuner train /root/ft/config/internlm2_1_8b_qlora_alpaca_e3_copy.py --work-dir /root/ft/train_deepspeed --deepspeed deepspeed_zero2 # deepspeed

xtuner确实方便，几条指令就能直接开始训练了，而且支持使用自己的数据集，比我之前自己做qlora微调方便了非常多，而且config文件也写得很清楚明了，不用花很多时间去理解，一看就懂，还是很方便的

模型部署

将模型转换为Huggingface格式

mkdir -p /root/ft/huggingface

# 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_896.pth /root/ft/huggingface

组合Lora得到的Adapter和原模型

这个xtuner也能一键整合，超方便

# 存储整合后的模型文件
mkdir -p /root/ft/final_model

export MKL_SERVICE_FORCE_INTEL=1

xtuner convert merge /root/ft/model /root/ft/huggingface /root/ft/final_model

xtuner支持在终端直接与Huggingface格式的模型进行对话，可以测试整合后的模型的性能，真的好方便……………………………………

xtuner chat /root/ft/final_model --prompt-template internlm2_chat

Web demo部署

# 安装依赖和拉取InterLM项目代码
pip install streamlit==1.24.0

mkdir -p /root/ft/web_demo && cd /root/ft/web_demo

git clone https://github.com/InternLM/InternLM.git

cd /root/ft/web_demo/InternLM

将 /root/ft/web_demo/InternLM/chat/web_demo.py中的内容替换为以下的代码

"""This script refers to the dialogue example of streamlit, the interactive
generation code of chatglm2 and transformers.

We mainly modified part of the code logic to adapt to the
generation of our model.
Please refer to these links below for more information:
    1. streamlit chat example:
        https://docs.streamlit.io/knowledge-base/tutorials/build-conversational-apps
    2. chatglm2:
        https://github.com/THUDM/ChatGLM2-6B
    3. transformers:
        https://github.com/huggingface/transformers
Please run with the command `streamlit run path/to/web_demo.py
    --server.address=0.0.0.0 --server.port 7860`.
Using `python path/to/web_demo.py` may cause unknown problems.
"""
# isort: skip_file
import copy
import warnings
from dataclasses import asdict, dataclass
from typing import Callable, List, Optional

import streamlit as st
import torch
from torch import nn
from transformers.generation.utils import (LogitsProcessorList,
                                           StoppingCriteriaList)
from transformers.utils import logging

from transformers import AutoTokenizer, AutoModelForCausalLM  # isort: skip

logger = logging.get_logger(__name__)


@dataclass
class GenerationConfig:
    # this config is used for chat to provide more diversity
    max_length: int = 2048
    top_p: float = 0.75
    temperature: float = 0.1
    do_sample: bool = True
    repetition_penalty: float = 1.000


@torch.inference_mode()
def generate_interactive(
    model,
    tokenizer,
    prompt,
    generation_config: Optional[GenerationConfig] = None,
    logits_processor: Optional[LogitsProcessorList] = None,
    stopping_criteria: Optional[StoppingCriteriaList] = None,
    prefix_allowed_tokens_fn: Optional[Callable[[int, torch.Tensor],
                                                List[int]]] = None,
    additional_eos_token_id: Optional[int] = None,
    **kwargs,
):
    inputs = tokenizer([prompt], padding=True, return_tensors='pt')
    input_length = len(inputs['input_ids'][0])
    for k, v in inputs.items():
        inputs[k] = v.cuda()
    input_ids = inputs['input_ids']
    _, input_ids_seq_length = input_ids.shape[0], input_ids.shape[-1]
    if generation_config is None:
        generation_config = model.generation_config
    generation_config = copy.deepcopy(generation_config)
    model_kwargs = generation_config.update(**kwargs)
    bos_token_id, eos_token_id = (  # noqa: F841  # pylint: disable=W0612
        generation_config.bos_token_id,
        generation_config.eos_token_id,
    )
    if isinstance(eos_token_id, int):
        eos_token_id = [eos_token_id]
    if additional_eos_token_id is not None:
        eos_token_id.append(additional_eos_token_id)
    has_default_max_length = kwargs.get(
        'max_length') is None and generation_config.max_length is not None
    if has_default_max_length and generation_config.max_new_tokens is None:
        warnings.warn(
            f"Using 'max_length''s default ({repr(generation_config.max_length)}) \
                to control the generation length. "
            'This behaviour is deprecated and will be removed from the \
                config in v5 of Transformers -- we'
            ' recommend using `max_new_tokens` to control the maximum \
                length of the generation.',
            UserWarning,
        )
    elif generation_config.max_new_tokens is not None:
        generation_config.max_length = generation_config.max_new_tokens + \
            input_ids_seq_length
        if not has_default_max_length:
            logger.warn(  # pylint: disable=W4902
                f"Both 'max_new_tokens' (={generation_config.max_new_tokens}) "
                f"and 'max_length'(={generation_config.max_length}) seem to "
                "have been set. 'max_new_tokens' will take precedence. "
                'Please refer to the documentation for more information. '
                '(https://huggingface.co/docs/transformers/main/'
                'en/main_classes/text_generation)',
                UserWarning,
            )

    if input_ids_seq_length >= generation_config.max_length:
        input_ids_string = 'input_ids'
        logger.warning(
            f"Input length of {input_ids_string} is {input_ids_seq_length}, "
            f"but 'max_length' is set to {generation_config.max_length}. "
            'This can lead to unexpected behavior. You should consider'
            " increasing 'max_new_tokens'.")

    # 2. Set generation parameters if not already defined
    logits_processor = logits_processor if logits_processor is not None \
        else LogitsProcessorList()
    stopping_criteria = stopping_criteria if stopping_criteria is not None \
        else StoppingCriteriaList()

    logits_processor = model._get_logits_processor(
        generation_config=generation_config,
        input_ids_seq_length=input_ids_seq_length,
        encoder_input_ids=input_ids,
        prefix_allowed_tokens_fn=prefix_allowed_tokens_fn,
        logits_processor=logits_processor,
    )

    stopping_criteria = model._get_stopping_criteria(
        generation_config=generation_config,
        stopping_criteria=stopping_criteria)
    logits_warper = model._get_logits_warper(generation_config)

    unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1)
    scores = None
    while True:
        model_inputs = model.prepare_inputs_for_generation(
            input_ids, **model_kwargs)
        # forward pass to get next token
        outputs = model(
            **model_inputs,
            return_dict=True,
            output_attentions=False,
            output_hidden_states=False,
        )

        next_token_logits = outputs.logits[:, -1, :]

        # pre-process distribution
        next_token_scores = logits_processor(input_ids, next_token_logits)
        next_token_scores = logits_warper(input_ids, next_token_scores)

        # sample
        probs = nn.functional.softmax(next_token_scores, dim=-1)
        if generation_config.do_sample:
            next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)
        else:
            next_tokens = torch.argmax(probs, dim=-1)

        # update generated ids, model inputs, and length for next step
        input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)
        model_kwargs = model._update_model_kwargs_for_generation(
            outputs, model_kwargs, is_encoder_decoder=False)
        unfinished_sequences = unfinished_sequences.mul(
            (min(next_tokens != i for i in eos_token_id)).long())

        output_token_ids = input_ids[0].cpu().tolist()
        output_token_ids = output_token_ids[input_length:]
        for each_eos_token_id in eos_token_id:
            if output_token_ids[-1] == each_eos_token_id:
                output_token_ids = output_token_ids[:-1]
        response = tokenizer.decode(output_token_ids)

        yield response
        # stop when each sentence is finished
        # or if we exceed the maximum length
        if unfinished_sequences.max() == 0 or stopping_criteria(
                input_ids, scores):
            break


def on_btn_click():
    del st.session_state.messages


@st.cache_resource
def load_model():
    model = (AutoModelForCausalLM.from_pretrained('/root/ft/final_model',
                                                  trust_remote_code=True).to(
                                                      torch.bfloat16).cuda())
    tokenizer = AutoTokenizer.from_pretrained('/root/ft/final_model',
                                              trust_remote_code=True)
    return model, tokenizer


def prepare_generation_config():
    with st.sidebar:
        max_length = st.slider('Max Length',
                               min_value=8,
                               max_value=32768,
                               value=2048)
        top_p = st.slider('Top P', 0.0, 1.0, 0.75, step=0.01)
        temperature = st.slider('Temperature', 0.0, 1.0, 0.1, step=0.01)
        st.button('Clear Chat History', on_click=on_btn_click)

    generation_config = GenerationConfig(max_length=max_length,
                                         top_p=top_p,
                                         temperature=temperature)

    return generation_config


user_prompt = '<|im_start|>user\n{user}<|im_end|>\n'
robot_prompt = '<|im_start|>assistant\n{robot}<|im_end|>\n'
cur_query_prompt = '<|im_start|>user\n{user}<|im_end|>\n\
    <|im_start|>assistant\n'


def combine_history(prompt):
    messages = st.session_state.messages
    meta_instruction = ('')
    total_prompt = f"<s><|im_start|>system\n{meta_instruction}<|im_end|>\n"
    for message in messages:
        cur_content = message['content']
        if message['role'] == 'user':
            cur_prompt = user_prompt.format(user=cur_content)
        elif message['role'] == 'robot':
            cur_prompt = robot_prompt.format(robot=cur_content)
        else:
            raise RuntimeError
        total_prompt += cur_prompt
    total_prompt = total_prompt + cur_query_prompt.format(user=prompt)
    return total_prompt


def main():
    # torch.cuda.empty_cache()
    print('load model begin.')
    model, tokenizer = load_model()
    print('load model end.')


    st.title('InternLM2-Chat-1.8B')

    generation_config = prepare_generation_config()

    # Initialize chat history
    if 'messages' not in st.session_state:
        st.session_state.messages = []

    # Display chat messages from history on app rerun
    for message in st.session_state.messages:
        with st.chat_message(message['role'], avatar=message.get('avatar')):
            st.markdown(message['content'])

    # Accept user input
    if prompt := st.chat_input('What is up?'):
        # Display user message in chat message container
        with st.chat_message('user'):
            st.markdown(prompt)
        real_prompt = combine_history(prompt)
        # Add user message to chat history
        st.session_state.messages.append({
            'role': 'user',
            'content': prompt,
        })

        with st.chat_message('robot'):
            message_placeholder = st.empty()
            for cur_response in generate_interactive(
                    model=model,
                    tokenizer=tokenizer,
                    prompt=real_prompt,
                    additional_eos_token_id=92542,
                    **asdict(generation_config),
            ):
                # Display robot response in chat message container
                message_placeholder.markdown(cur_response + '▌')
            message_placeholder.markdown(cur_response)
        # Add robot response to chat history
        st.session_state.messages.append({
            'role': 'robot',
            'content': cur_response,  # pylint: disable=undefined-loop-variable
        })
        torch.cuda.empty_cache()


if __name__ == '__main__':
    main()

运行

streamlit run /root/ft/web_demo/InternLM/chat/web_demo.py --server.address 127.0.0.1 --server.port 6006