XTuner微调个人小助手认知

最新推荐文章于 2025-05-09 11:31:15 发布

11子贤

最新推荐文章于 2025-05-09 11:31:15 发布

阅读量690

点赞数 15

CC 4.0 BY-SA版权

分类专栏：书生万象训练营文章标签：人工智能

本文链接：https://blog.csdn.net/weixin_42037035/article/details/140956433

一、准备工作

1.准备开发机

2.创建虚拟环境

# 创建虚拟环境
conda create -n xtuner0121 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 xtuner0121

# 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
pip install transformers==4.39.3
pip install streamlit==1.36.0

3.安装 XTuner

# 创建一个目录，用来存放源代码
mkdir -p /root/InternLM/code

cd /root/InternLM/code

git clone -b v0.1.21  https://github.com/InternLM/XTuner /root/InternLM/code/XTuner

进入源码目录，执行安装

# 进入到源码目录
cd /root/InternLM/code/XTuner
conda activate xtuner0121

# 执行安装
pip install -e '.[deepspeed]'
#镜像加速版
pip install -e '.[deepspeed]' -i https://mirrors.aliyun.com/pypi/simple/

速度较慢，耐心等待

验证一下安装结果

xtuner version

查看相关的帮助

xtuner help

4.模型准备

通过以下代码一键通过符号链接的方式链接到模型文件，这样既节省了空间，也便于管理

# 创建一个目录，用来存放微调的所有资料，后续的所有操作都在该路径中进行
mkdir -p /root/InternLM/XTuner

cd /root/InternLM/XTuner

mkdir -p Shanghai_AI_Laboratory

ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b Shanghai_AI_Laboratory/internlm2-chat-1_8b

执行上述操作后，Shanghai_AI_Laboratory/internlm2-chat-1_8b 将直接成为一个符号链接，这个链接指向 /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b 的位置。

这意味着，当我们访问 Shanghai_AI_Laboratory/internlm2-chat-1_8b 时，实际上就是在访问 /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b 目录下的内容。通过这种方式，我们无需复制任何数据，就可以直接利用现有的模型文件进行后续的微调操作，从而节省存储空间并简化文件管理。

模型文件准备好后，我们可以使用tree命令来观察目录结构。

apt-get install -y tree

tree -l

在目录结构中可以看出，internlm2-chat-1_8b 是一个符号链接

二、快速开始

这里我们用 internlm2-chat-1_8b 模型，通过 QLoRA 的方式来微调一个自己的小助手认知作为案例来进行演示

1.微调前的模型对话

准备一个Streamlit程序的脚本

新建文件xtuner_streamlit_demo.py

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__)


model_name_or_path = "/root/InternLM/XTuner/Shanghai_AI_Laboratory/internlm2-chat-1_8b"

@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=st