OracleWindows环境下搭建Qwen开发环境 - Powered by Discuz! Archiver

商道如狼道 发表于 2024-11-25 01:05:02

Windows环境下搭建Qwen开发环境

1 参考文献

【官方指引】https://qwen.readthedocs.io/en/latest/
【ModelScope训练】https://modelscope.cn/docs/%E4%BD%BF%E7%94%A8Tuners
【CUDA下载安装教程】https://blog.csdn.net/changyana/article/details/135876568
【安装cuDNN】https://developer.nvidia.com/rdp/cudnn-archive
【安装PyTorch】https://pytorch.org/
【安装Ollama】https://ollama.com/download
2 底子环境

2.1 安装CUDA

【检察显卡驱动】nvidia-smi
【验证CUDA安装】nvcc -V
首先查看NVIDIA显卡对应的CUDA版本号，然后根据此版本号下载对应版本的Toolkit
https://img-blog.csdnimg.cn/img_convert/d35c4c4a707aaf5cba07ee2545b96f61.png
2.2 安装cuDNN

https://img-blog.csdnimg.cn/img_convert/41c6b24cd40b60bc798b8df67a0386ad.png
把下载的cudnn压缩包进行解压，在cudnn的文件夹下，把bin，include，lib文件夹下的内容对应拷贝到cuda相应的bin，include，lib下即可，最后安装完成。
2.3 安装PyTorch

https://img-blog.csdnimg.cn/img_convert/047b2305d830c02a931c7a613c23c354.png
https://img-blog.csdnimg.cn/img_convert/b16d12820d18612374b54c413ec3b410.png
# 验证PyTorch是否与CUDA兼容

import torch

print(torch.\_\_version\_\_)
print(torch.cuda.is\_available())
3 通过Ollama调用模子

Ollama是一种比较简单方便的当地运行方案。通过Ollama官网直接安装，可搜索支持的大模子：https://ollama.com/search?q=qwen
https://img-blog.csdnimg.cn/img_convert/ac65178abe6cd05cd50d73272b6ac9fe.png
4 Qwen官方指引

Qwen官方指南具体说明白支持的各种方案，比检察各种网络博客说明更清晰。
https://img-blog.csdnimg.cn/img_convert/de0dc39a9b94b7b544069c3dbec73bb1.png
5 自界说训练

5.1 参考ModelScope指引

\# 自定义ModelScope模型缓存路径
export MODELSCOPE\_CACHE\=/Users/kuliuheng/workspace/aiWorkspace/Qwen
https://img-blog.csdnimg.cn/img_convert/ef77ce7a839b8d6f77aada696d8e5d82.gifhttps://img-blog.csdnimg.cn/img_convert/56146fbdebd07ebeb5f202dd8ab98114.gif
1 # A100 18G memory
2 from swift import Seq2SeqTrainer, Seq2SeqTrainingArguments 3 from modelscope import MsDataset, AutoTokenizer 4 from modelscope import AutoModelForCausalLM 5 from swift import Swift, LoraConfig 6 from swift.llm import get\_template, TemplateType 7 import torch 8
9 pretrained\_model = 'qwen/Qwen2.5-0.5B-Instruct'
10
11
12 def encode(example):
13 inst, inp, output = example\['instruction'\], example.get('input', None), example\['output'\]
14 if output is None:
15       return {}
16 if inp is None or len(inp) == 0:
17       q = inst
18 else:
19       q = f'{inst}\\n{inp}'
20 example, kwargs = template.encode({'query': q, 'response': output})
21 return example
22
23
24 if \_\_name\_\_ == '\_\_main\_\_':
25 # 拉起模型
26 model = AutoModelForCausalLM.from\_pretrained(pretrained\_model, torch\_dtype=torch.bfloat16, device\_map='auto', trust\_remote\_code=True)
27 lora\_config = LoraConfig(
28                   r=8,
29                   bias='none',
30                   task\_type="CAUSAL\_LM",
31                   target\_modules=\["q\_proj", "k\_proj", "v\_proj", "o\_proj"\],
32                   lora\_alpha=32,
33                   lora\_dropout=0.05)
34 model = Swift.prepare\_model(model, lora\_config)
35 tokenizer = AutoTokenizer.from\_pretrained(pretrained\_model, trust\_remote\_code=True)
36 dataset = MsDataset.load('AI-ModelScope/alpaca-gpt4-data-en', split='train')
37 template = get\_template(TemplateType.chatglm3, tokenizer, max\_length=1024)
38
39 dataset = dataset.map(encode).filter(lambda e: e.get('input\_ids'))
40 dataset = dataset.train\_test\_split(test\_size=0.001)
41
42 train\_dataset, val\_dataset = dataset\['train'\], dataset\['test'\]
43
44 train\_args = Seq2SeqTrainingArguments(
45       output\_dir='output',
46       learning\_rate=1e-4,
47       num\_train\_epochs=2,
48       eval\_steps=500,
49       save\_steps=500,
50       evaluation\_strategy='steps',
51       save\_strategy='steps',
52       dataloader\_num\_workers=4,
53       per\_device\_train\_batch\_size=1,
54       gradient\_accumulation\_steps=16,
55       logging\_steps=10,
56 )
57
58 trainer = Seq2SeqTrainer(
59       model=model,
60       args=train\_args,
61       data\_collator=template.data\_collator,
62       train\_dataset=train\_dataset,
63       eval\_dataset=val\_dataset,
64       tokenizer=tokenizer)
65
66 trainer.train()
View Code
（1）官方示例代码中没有写 __main__ 主函数入口，实际运行时发现会报错提示说：子线程在主线程尚未完成初始化之前就运行了。所以这里就补齐了一个主函数入口
（2）官方代码中没有针对 ‘qwen/Qwen2.5-0.5B-Instruct’ 模子代码，运行时target_modules会提示错误，需要指定模子中实际存在的模块名才行。这里有个技巧，通过打印模子信息可以看到实际的层级结构：
from modelscope import AutoModelForCausalLM

model\_name \= 'qwen/Qwen2.5-0.5B-Instruct'
model \= AutoModelForCausalLM.from\_pretrained(model\_name)
print(model)
得到如下结果：
https://img-blog.csdnimg.cn/img_convert/9659b198864805cd9ab216bf2a25c1ff.gifhttps://img-blog.csdnimg.cn/img_convert/db079ae0f97aa2809c9708b9918181b6.gif
Qwen2ForCausalLM(
(model): Qwen2Model(
(embed\_tokens): Embedding(151936, 896)
(layers): ModuleList(
   (0\-23): 24 x Qwen2DecoderLayer(
   (self\_attn): Qwen2SdpaAttention(
      (q\_proj): Linear(in\_features\=896, out\_features=896, bias=True)
      (k\_proj): Linear(in\_features\=896, out\_features=128, bias=True)
      (v\_proj): Linear(in\_features\=896, out\_features=128, bias=True)
      (o\_proj): Linear(in\_features\=896, out\_features=896, bias=False)
      (rotary\_emb): Qwen2RotaryEmbedding()
   )
   (mlp): Qwen2MLP(
      (gate\_proj): Linear(in\_features\=896, out\_features=4864, bias=False)
      (up\_proj): Linear(in\_features\=896, out\_features=4864, bias=False)
      (down\_proj): Linear(in\_features\=4864, out\_features=896, bias=False)
      (act\_fn): SiLU()
   )
   (input\_layernorm): Qwen2RMSNorm((896,), eps=1e-06)
   (post\_attention\_layernorm): Qwen2RMSNorm((896,), eps=1e-06)
   )
)
(norm): Qwen2RMSNorm((896,), eps=1e-06)
(rotary\_emb): Qwen2RotaryEmbedding()
)
(lm\_head): Linear(in\_features\=896, out\_features=151936, bias=False)
)
View Code
调整目标模块名之后，代码能够跑起来了，但Mac Apple M3笔记本上跑，的确是速度太慢了点：
\ Successfully registered \`/Users/kuliuheng/workspace/aiWorkspace/Qwen/testMS/.venv/lib/python3.10/site-packages/swift/llm/data/dataset\_info.json\`
\ No vLLM installed, if you are using vLLM, you will get \`ImportError: cannot import name 'get\_vllm\_engine' from 'swift.llm'\`
\ No LMDeploy installed, if you are using LMDeploy, you will get \`ImportError: cannot import name 'prepare\_lmdeploy\_engine\_template' from 'swift.llm'\`
Train: 0%|       | 10/6492 \{'loss': 20.66802063, 'acc': 0.66078668, 'grad\_norm': 30.34488869, 'learning\_rate': 9.985e-05, 'memory(GiB)': 0, 'train\_speed(iter/s)': 0.048214, 'epoch': 0.0, 'global\_step/max\_steps': '10/6492', 'percentage': '0.15%', 'elapsed\_time': '3m 27s', 'remaining\_time': '1d 13h 21m 21s'}
Train: 0%|       | 20/6492 \{'loss': 21.01838379, 'acc': 0.66624489, 'grad\_norm': 23.78275299, 'learning\_rate': 9.969e-05, 'memory(GiB)': 0, 'train\_speed(iter/s)': 0.014436, 'epoch': 0.01, 'global\_step/max\_steps': '20/6492', 'percentage': '0.31%', 'elapsed\_time': '23m 5s', 'remaining\_time': '5d 4h 31m 21s'}
Train: 0%|       | 30/6492 \{'loss': 20.372052, 'acc': 0.67057648, 'grad\_norm': 38.68712616, 'learning\_rate': 9.954e-05, 'memory(GiB)': 0, 'train\_speed(iter/s)': 0.016769, 'epoch': 0.01, 'global\_step/max\_steps': '30/6492', 'percentage': '0.46%', 'elapsed\_time': '29m 48s', 'remaining\_time': '4d 11h 2m 20s'}
Train: 1%|       | 40/6492 \{'loss': 20.92590179, 'acc': 0.66806035, 'grad\_norm': 38.17282486, 'learning\_rate': 9.938e-05, 'memory(GiB)': 0, 'train\_speed(iter/s)': 0.018514, 'epoch': 0.01, 'global\_step/max\_steps': '40/6492', 'percentage': '0.62%', 'elapsed\_time': '36m 0s', 'remaining\_time': '4d 0h 48m 3s'}
Train: 1%|       | 50/6492 \{'loss': 19.25114594, 'acc': 0.68523092, 'grad\_norm': 37.24295807, 'learning\_rate': 9.923e-05, 'memory(GiB)': 0, 'train\_speed(iter/s)': 0.01966, 'epoch': 0.02, 'global\_step/max\_steps': '50/6492', 'percentage': '0.77%', 'elapsed\_time': '42m 23s', 'remaining\_time': '3d 19h 1m 0s'}
Train: 1%|       | 60/6492 \{'loss': 19.54689178, 'acc': 0.69552717, 'grad\_norm': 27.87804794, 'learning\_rate': 9.908e-05, 'memory(GiB)': 0, 'train\_speed(iter/s)': 0.020941, 'epoch': 0.02, 'global\_step/max\_steps': '60/6492', 'percentage': '0.92%', 'elapsed\_time': '47m 45s', 'remaining\_time': '3d 13h 19m 3s'}
Train: 1%|       | 65/6492 \

免责声明：如果侵犯了您的权益，请联系站长，我们会及时删除侵权内容，谢谢合作！更多信息从访问主页：qidao123.com:ToB企服之家，中国第一个企服评测及商务社交产业平台。

页: [1]

ToB企服应用市场:ToB评测及商务社交产业平台's Archiver

Windows环境下搭建Qwen开发环境