浦语大模型4_hw_base

XTuner 大模型单卡低成本微调实战

https://github.com/InternLM/tutorial/blob/main/xtuner/self.md

环境准备

# InternStudio 平台中，从本地 clone 一个已有 pytorch 2.0.1 的环境（后续均在该环境执行，若为其他环境可作为参考）
# 进入环境后首先 bash
# 进入环境后首先 bash
# 进入环境后首先 bash
bash
conda create --name personal_assistant --clone=/root/share/conda_envs/internlm-base
# 如果在其他平台：
# conda create --name personal_assistant python=3.10 -y

# 激活环境
conda activate personal_assistant
# 进入家目录 （~的意思是 “当前用户的home路径”）
cd ~
# 创建版本文件夹并进入，以跟随本教程
# personal_assistant用于存放本教程所使用的东西
mkdir /root/personal_assistant && cd /root/personal_assistant
mkdir /root/personal_assistant/xtuner019 && cd /root/personal_assistant/xtuner019

# 拉取 0.1.9 的版本源码
git clone -b v0.1.9  https://github.com/InternLM/xtuner
# 无法访问github的用户请从 gitee 拉取:
# git clone -b v0.1.9 https://gitee.com/Internlm/xtuner

# 进入源码目录
cd xtuner

# 从源码安装 XTuner
pip install -e '.[all]'


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

import json

# 输入你的名字
name = 'Shengshenlan'
# 重复次数
n = 10000

data = [
    {
        "conversation": [
            {
                "input": "请做一下自我介绍",
                "output": "我是{}的小助手，内在是上海AI实验室书生·浦语的7B大模型哦".format(name)
            }
        ]
    }
]

for i in range(n):
    data.append(data[0])

with open('personal_assistant.json', 'w', encoding='utf-8') as f:
    json.dump(data, f, ensure_ascii=False, indent=4)

下载模型InternLM-chat-7B

mkdir -p /root/personal_assistant/model/Shanghai_AI_Laboratory
cp -r /root/share/temp/model_repos/internlm-chat-7b /root/personal_assistant/model/Shanghai_AI_Laboratory

# 列出所有内置配置
xtuner list-cfg

# Copyright (c) OpenMMLab. All rights reserved.
import torch
from bitsandbytes.optim import PagedAdamW32bit
from datasets import load_dataset
from mmengine.dataset import DefaultSampler
from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook,
                            LoggerHook, ParamSchedulerHook)
from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR
from peft import LoraConfig
from transformers import (AutoModelForCausalLM, AutoTokenizer,
                          BitsAndBytesConfig)

from xtuner.dataset import process_hf_dataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.map_fns import oasst1_map_fn, template_map_fn_factory
from xtuner.engine import DatasetInfoHook, EvaluateChatHook
from xtuner.model import SupervisedFinetune
from xtuner.utils import PROMPT_TEMPLATE

#######################################################################
#                          PART 1  Settings                           #
#######################################################################
# Model
pretrained_model_name_or_path = '/root/personal_assistant/model/Shanghai_AI_Laboratory/internlm-chat-7b'

# Data
data_path = '/root/personal_assistant/data/personal_assistant.json'
prompt_template = PROMPT_TEMPLATE.internlm_chat
max_length = 512
pack_to_max_length = True

# Scheduler & Optimizer
batch_size = 2  # per_device
accumulative_counts = 16
dataloader_num_workers = 0
max_epochs = 3
optim_type = PagedAdamW32bit
lr = 2e-4
betas = (0.9, 0.999)
weight_decay = 0
max_norm = 1  # grad clip

# Evaluate the generation performance during the training
evaluation_freq = 90
SYSTEM = ''
evaluation_inputs = [ '请介绍一下你自己', '请做一下自我介绍' ]

#######################################################################
#                      PART 2  Model & Tokenizer                      #
#######################################################################
tokenizer = dict(
    type=AutoTokenizer.from_pretrained,
    pretrained_model_name_or_path=pretrained_model_name_or_path,
    trust_remote_code=True,
    padding_side='right')

model = dict(
    type=SupervisedFinetune,
    llm=dict(
        type=AutoModelForCausalLM.from_pretrained,
        pretrained_model_name_or_path=pretrained_model_name_or_path,
        trust_remote_code=True,
        torch_dtype=torch.float16,
        quantization_config=dict(
            type=BitsAndBytesConfig,
            load_in_4bit=True,
            load_in_8bit=False,
            llm_int8_threshold=6.0,
            llm_int8_has_fp16_weight=False,
            bnb_4bit_compute_dtype=torch.float16,
            bnb_4bit_use_double_quant=True,
            bnb_4bit_quant_type='nf4')),
    lora=dict(
        type=LoraConfig,
        r=64,
        lora_alpha=16,
        lora_dropout=0.1,
        bias='none',
        task_type='CAUSAL_LM'))

#######################################################################
#                      PART 3  Dataset & Dataloader                   #
#######################################################################
train_dataset = dict(
    type=process_hf_dataset,
    dataset=dict(type=load_dataset, path='json', data_files=dict(train=data_path)),
    tokenizer=tokenizer,
    max_length=max_length,
    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)

train_dataloader = dict(
    batch_size=batch_size,
    num_workers=dataloader_num_workers,
    dataset=train_dataset,
    sampler=dict(type=DefaultSampler, shuffle=True),
    collate_fn=dict(type=default_collate_fn))

#######################################################################
#                    PART 4  Scheduler & Optimizer                    #
#######################################################################
# optimizer
optim_wrapper = dict(
    type=AmpOptimWrapper,
    optimizer=dict(
        type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay),
    clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False),
    accumulative_counts=accumulative_counts,
    loss_scale='dynamic',
    dtype='float16')

# learning policy
# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md  # noqa: E501
param_scheduler = dict(
    type=CosineAnnealingLR,
    eta_min=0.0,
    by_epoch=True,
    T_max=max_epochs,
    convert_to_iter_based=True)

# train, val, test setting
train_cfg = dict(by_epoch=True, max_epochs=max_epochs, val_interval=1)

#######################################################################
#                           PART 5  Runtime                           #
#######################################################################
# Log the dialogue periodically during the training process, optional
custom_hooks = [
    dict(type=DatasetInfoHook, tokenizer=tokenizer),
    dict(
        type=EvaluateChatHook,
        tokenizer=tokenizer,
        every_n_iters=evaluation_freq,
        evaluation_inputs=evaluation_inputs,
        system=SYSTEM,
        prompt_template=prompt_template)
]

# configure default hooks
default_hooks = dict(
    # record the time of every iteration.
    timer=dict(type=IterTimerHook),
    # print log every 100 iterations.
    logger=dict(type=LoggerHook, interval=10),
    # enable the parameter scheduler.
    param_scheduler=dict(type=ParamSchedulerHook),
    # save checkpoint per epoch.
    checkpoint=dict(type=CheckpointHook, interval=1),
    # set sampler seed in distributed evrionment.
    sampler_seed=dict(type=DistSamplerSeedHook),
)

# configure environment
env_cfg = dict(
    # whether to enable cudnn benchmark
    cudnn_benchmark=False,
    # set multi process parameters
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    # set distributed parameters
    dist_cfg=dict(backend='nccl'),
)

# set visualizer
visualizer = None

# set log level
log_level = 'INFO'

# load from which checkpoint
load_from = None

# whether to resume training from the loaded checkpoint
resume = False

# Defaults to use random seed and disable `deterministic`
randomness = dict(seed=None, deterministic=False)

 开始训练

xtuner train /root/personal_assistant/config/internlm_chat_7b_qlora_oasst1_e3_copy.py

两个epoch已经成功了

# 创建用于存放Hugging Face格式参数的hf文件夹
mkdir /root/personal_assistant/config/work_dirs/hf

export MKL_SERVICE_FORCE_INTEL=1

# 配置文件存放的位置
export CONFIG_NAME_OR_PATH=/root/personal_assistant/config/internlm_chat_7b_qlora_oasst1_e3_copy.py

# 模型训练后得到的pth格式参数存放的位置
export PTH=/root/personal_assistant/config/work_dirs/internlm_chat_7b_qlora_oasst1_e3_copy/epoch_3.pth

# pth文件转换为Hugging Face格式后参数存放的位置
export SAVE_PATH=/root/personal_assistant/config/work_dirs/hf

# 执行参数转换
xtuner convert pth_to_hf $CONFIG_NAME_OR_PATH $PTH $SAVE_PATH



export MKL_SERVICE_FORCE_INTEL=1
export MKL_THREADING_LAYER='GNU'

# 原始模型参数存放的位置
export NAME_OR_PATH_TO_LLM=/root/personal_assistant/model/Shanghai_AI_Laboratory/internlm-chat-7b

# Hugging Face格式参数存放的位置
export NAME_OR_PATH_TO_ADAPTER=/root/personal_assistant/config/work_dirs/hf

# 最终Merge后的参数存放的位置
mkdir /root/personal_assistant/config/work_dirs/hf_merge
export SAVE_PATH=/root/personal_assistant/config/work_dirs/hf_merge

# 执行参数Merge
xtuner convert merge \
    $NAME_OR_PATH_TO_LLM \
    $NAME_OR_PATH_TO_ADAPTER \
    $SAVE_PATH \
    --max-shard-size 2GB

pip install streamlit==1.24.0

# 创建code文件夹用于存放InternLM项目代码
mkdir /root/personal_assistant/code && cd /root/personal_assistant/code
git clone https://github.com/InternLM/InternLM.git

#此处疑似有误，因为InternLM/下没有web_demo.py,也许是我弄错了
#我用的InternLM/chat/web_demo.py
streamlit run /root/personal_assistant/code/InternLM/web_demo.py --server.address 127.0.0.1 --server.port 6006