当前位置：首页 > news >正文

产品盘网站建设广州从化发布

news 2026/4/8 17:46:12

产品盘网站建设,广州从化发布,重庆网站建设论坛,电话怎么做网站域名前言使用XTuner 微调个人小助手认知一、下载模型 #安装魔搭依赖包 pip install modelscope新建download.py内容如下其中Shanghai_AI_Laboratory/internlm2-chat-1_8b是魔搭对应的模型ID cache_dir/home/aistudio/data/model’为指定下载到本地的目录 from modelscope im…

前言

使用XTuner 微调个人小助手认知

一、下载模型

#安装魔搭依赖包
pip install modelscope

新建download.py内容如下
其中Shanghai_AI_Laboratory/internlm2-chat-1_8b是魔搭对应的模型ID
cache_dir='/home/aistudio/data/model’为指定下载到本地的目录

from modelscope import snapshot_download
model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm2-chat-1_8b',cache_dir='/home/aistudio/data/model')

二、安装 XTuner

1.创建环境

#新建一个code文件夹
mkdir -p /home/aistudio/data/code
#切换到该目录下
cd /home/aistudio/data/code
#从 Github 上下载源码
git clone -b v0.1.21  https://github.com/InternLM/XTuner
#进入源码目录
cd XTuner
# 执行安装
pip install -e '.[deepspeed]'

2.结果验证

xtuner version

三. 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.准备数据

#新建datas文件夹
mkdir -p datas
#创建json文件
touch datas/assistant.json

2.数据生成

1.新建一个xtuner_generate_assistant.py内容如下
2.修改neme由“伍鲜同志”改为“阿豪”
3.修改数据写入路径为刚刚创建的json文件

import json# 设置用户的名字
name = '阿豪'
# 设置需要重复添加的数据次数
n = 8000# 初始化数据
data = [{"conversation": [{"input": "请介绍一下你自己", "output": "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".format(name)}]},{"conversation": [{"input": "你在实战营做什么", "output": "我在这里帮助{}完成XTuner微调个人小助手的任务".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])data.append(data[1])# 将data列表中的数据写入到'datas/assistant.json'文件中
with open('datas/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)

3.初始化数据

#执行
python xtuner_generate_assistant.py

在这里插入图片描述

4.获取训练脚本

xtuner copy-cfg internlm2_chat_1_8b_qlora_alpaca_e3 .

修改内容如下

# Copyright (c) OpenMMLab. All rights reserved.
import torch
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, LinearLR
from peft import LoraConfig
from torch.optim import AdamW
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 alpaca_map_fn, template_map_fn_factory
from xtuner.engine.hooks import (DatasetInfoHook, EvaluateChatHook,VarlenAttnArgsToMessageHubHook)
from xtuner.engine.runner import TrainLoop
from xtuner.model import SupervisedFinetune
from xtuner.parallel.sequence import SequenceParallelSampler
from xtuner.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE#######################################################################
#                          PART 1  Settings                           #
#######################################################################
# Model
pretrained_model_name_or_path = '/mnt/workspace/model/Shanghai_AI_Laboratory/internlm2-chat-1_8b'
use_varlen_attn = False# Data
alpaca_en_path = '/mnt/workspace/code/datas/assistant.json'
prompt_template = PROMPT_TEMPLATE.internlm2_chat
max_length = 2048
pack_to_max_length = True# parallel
sequence_parallel_size = 1# Scheduler & Optimizer
batch_size = 1  # per_device
accumulative_counts = 16
accumulative_counts *= sequence_parallel_size
dataloader_num_workers = 0
max_epochs = 3
optim_type = AdamW
lr = 2e-4
betas = (0.9, 0.999)
weight_decay = 0
max_norm = 1  # grad clip
warmup_ratio = 0.03# Save
save_steps = 500
save_total_limit = 2  # Maximum checkpoints to keep (-1 means unlimited)# Evaluate the generation performance during the training
evaluation_freq = 500
SYSTEM = SYSTEM_TEMPLATE.alpaca
evaluation_inputs = ['请介绍一下你自己', 'Please introduce yourself'
]#######################################################################
#                      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,use_varlen_attn=use_varlen_attn,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                   #
#######################################################################
alpaca_en = dict(type=process_hf_dataset,dataset=dict(type=load_dataset, path='json', data_files=dict(train=alpaca_en_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,use_varlen_attn=use_varlen_attn)sampler = SequenceParallelSampler \if sequence_parallel_size > 1 else DefaultSampler
train_dataloader = dict(batch_size=batch_size,num_workers=dataloader_num_workers,dataset=alpaca_en,sampler=dict(type=sampler, shuffle=True),collate_fn=dict(type=default_collate_fn, use_varlen_attn=use_varlen_attn))#######################################################################
#                    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=LinearLR,start_factor=1e-5,by_epoch=True,begin=0,end=warmup_ratio * max_epochs,convert_to_iter_based=True),dict(type=CosineAnnealingLR,eta_min=0.0,by_epoch=True,begin=warmup_ratio * max_epochs,end=max_epochs,convert_to_iter_based=True)
]# train, val, test setting
train_cfg = dict(type=TrainLoop, max_epochs=max_epochs)#######################################################################
#                           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)
]if use_varlen_attn:custom_hooks += [dict(type=VarlenAttnArgsToMessageHubHook)]# configure default hooks
default_hooks = dict(# record the time of every iteration.timer=dict(type=IterTimerHook),# print log every 10 iterations.logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=10),# enable the parameter scheduler.param_scheduler=dict(type=ParamSchedulerHook),# save checkpoint per `save_steps`.checkpoint=dict(type=CheckpointHook,by_epoch=False,interval=save_steps,max_keep_ckpts=save_total_limit),# set sampler seed in distributed evrionment.sampler_seed=dict(type=DistSamplerSeedHook),
)# configure environment
env_cfg = dict(# whether to enable cudnn benchmarkcudnn_benchmark=False,# set multi process parametersmp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),# set distributed parametersdist_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)# set log processor
log_processor = dict(by_epoch=False)

5.开启训练

xtuner train ./internlm2_chat_1_8b_qlora_alpaca_e3_copy.py

在这里插入图片描述

微调前

在这里插入图片描述

6. 模型格式转换

pth_file=`ls -t ./work_dirs/internlm2_chat_1_8b_qlora_alpaca_e3_copy/*.pth | head -n 1`
export MKL_SERVICE_FORCE_INTEL=1
export MKL_THREADING_LAYER=GNU
xtuner convert pth_to_hf ./internlm2_chat_1_8b_qlora_alpaca_e3_copy.py ${pth_file} ./hf

在这里插入图片描述

7.模型合并

export MKL_SERVICE_FORCE_INTEL=1
export MKL_THREADING_LAYER=GNU
xtuner convert merge /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b ./hf ./merged --max-shard-size 2GB

在这里插入图片描述

8.测试效果

python -m streamlit run xtuner_streamlit_demo.py

在这里插入图片描述

查看全文

http://www.hkea.cn/news/668112/

最专业的佛山网站建设价格3小时百度收录新站方法

wordpress门户建站html网页完整代码作业

子域名做单独的网站广州seo外包公司

凡科建设网站的步骤永久免费无代码开发平台网站

wordpress自定义url优化教程网下载

模板网站和定制网站百度搜索引擎的网址

企业建设网站公司哪家好app拉新推广接单平台

老虎淘客系统可以做网站吗江西省水文监测中心

poedit pro wordpress免费网站推广优化

市场营销产品推广策划方案seo合作代理

东莞专业网站建设推广搜索引擎网络排名

服务器做网站用什么环境好销售营销方案100例

如何做DJ网站英文seo外链

网站统计源码下载百度推广的步骤

前言

一、下载模型

二、安装 XTuner

1.创建环境

2.结果验证

三. 快速开始

1.准备数据

2.数据生成

3.初始化数据

4.获取训练脚本

5.开启训练

微调前

6. 模型格式转换

7.模型合并

8.测试效果

相关文章：