subtitles/zh-CN/11_instantiate-a-transformers-model-(tensorflow).srt

1
00:00:00,125 --> 00:00:02,958
（嘶嘶声）
(whooshing sound)

2
00:00:05,463 --> 00:00:08,820
- 如何实例化 Transformers 模型？
- How to instantiate the Transformers model?

3
00:00:08,820 --> 00:00:11,250
在本视频中，我们将了解如何创建
In this video, we will look at how we can create

4
00:00:11,250 --> 00:00:13,550
并使用 Transformers 库中的模型。
and use a model from the Transformers library.

5
00:00:15,000 --> 00:00:17,850
正如我们之前看到的，TFAutoModel 类
As we've seen before, the TFAutoModel class

6
00:00:17,850 --> 00:00:20,100
允许你实例化预训练模型,
allows you to instantiate a pre-trained model

7
00:00:20,100 --> 00:00:22,503
从 Hugging Face Hub 上的任何一个 checkpoint。
from any checkpoint on the Hugging Face Hub.

8
00:00:23,430 --> 00:00:25,620
它将从库中选择正确的模型类
It will pick the right model class from the library

9
00:00:25,620 --> 00:00:27,750
来实例化适当的结构
to instantiate the proper architecture

10
00:00:27,750 --> 00:00:31,200
并在里面加载预训练模型的权重。
and load the weights of the pre-trained model inside.

11
00:00:31,200 --> 00:00:34,020
正如我们所见，当给定一个 BERT 的 checkpoint 时，
As we can see, when given a BERT checkpoint,

12
00:00:34,020 --> 00:00:36,090
我们最终得到一个 TFBertModel，
we end up with a TFBertModel,

13
00:00:36,090 --> 00:00:38,553
GPT2 或 BART 也类似。
and similarly for GPT2 or BART.

14
00:00:40,170 --> 00:00:42,510
在幕后，这个 API 接受 
Behind the scenes, this API can take the name

15
00:00:42,510 --> 00:00:44,040
Hub 上的一个 checkpoint 的名字，
of a checkpoint on the Hub,

16
00:00:44,040 --> 00:00:45,810
在这种情况下，它将下载并缓存
in which case it will download and cache

17
00:00:45,810 --> 00:00:48,660
配置文件以及模型权重文件。
the configuration file as well as the model weights file.

18
00:00:49,590 --> 00:00:52,020
你还可以指定本地文件夹的路径
You can also specify the path to a local folder

19
00:00:52,020 --> 00:00:54,090
包含有效的配置文件
that contains a valid configuration file

20
00:00:54,090 --> 00:00:55,340
和模型的权重文件。
and a model weights file.

21
00:00:56,670 --> 00:00:58,167
要实例化预训练模型，
To instantiate the pre-trained model,

22
00:00:58,167 --> 00:01:02,400
TFAutoModel API 会首先打开配置文件
the TFAutoModel API will first open the configuration file

23
00:01:02,400 --> 00:01:05,253
以查看应该使用的配置类。
to look at the configuration class that should be used.

24
00:01:06,390 --> 00:01:09,660
配置类取决于模型的类型，
The configuration class depends on the type of the model,

25
00:01:09,660 --> 00:01:12,333
例如 BERT、GPT2 或 BART。
BERT, GPT2 or BART for instance.

26
00:01:13,320 --> 00:01:15,720
一旦它有了正确的配置类，
Once it has the proper configuration class,

27
00:01:15,720 --> 00:01:18,000
它可以实例化该配置，
it can instantiate that configuration,

28
00:01:18,000 --> 00:01:21,090
这是了解如何创建模型的蓝图。
which is a blueprint to know how to create the model.

29
00:01:21,090 --> 00:01:22,770
它也使用这个配置类
It also uses this configuration class

30
00:01:22,770 --> 00:01:24,750
来找到合适的模型类，
to find the proper model class,

31
00:01:24,750 --> 00:01:27,120
它与加载的配置相结合
which is combined with the loaded configuration

32
00:01:27,120 --> 00:01:28,143
加载模型。
to load the model.

33
00:01:29,250 --> 00:01:31,800
这个模型还不是我们的预训练模型
This model is not yet our pre-trained model

34
00:01:31,800 --> 00:01:34,560
因为它刚刚用随机权重初始化。
as it has just been initialized with random weights.

35
00:01:34,560 --> 00:01:36,690
最后一步是加载权重
The last step is to load the weights

36
00:01:36,690 --> 00:01:38,973
从该模型中的模型文件中。
from the model file inside this model.

37
00:01:40,230 --> 00:01:42,270
为了轻松加载模型的配置, 
To easily load the configuration of a model

38
00:01:42,270 --> 00:01:44,220
从任何 checkpoint 或
from any checkpoint or 
39
00:01:44,220 --> 00:01:46,170
包含配置文件的文件夹，
a folder containing the configuration file,

40
00:01:46,170 --> 00:01:47,790
我们可以使用 AutoConfig 类。
we can use the AutoConfig class.

41
00:01:47,790 --> 00:01:50,460
与 TFAutoModel 类一样，
Like the TFAutoModel class,

42
00:01:50,460 --> 00:01:54,210
它将从库中选择正确的配置类。
it will pick the right configuration class from the library.

43
00:01:54,210 --> 00:01:56,040
我们也可以使用特定的类
We can also use the specific class

44
00:01:56,040 --> 00:01:57,840
对应一个 checkpoint ，
corresponding to a checkpoint,

45
00:01:57,840 --> 00:01:59,430
但我们需要更改代码
but we will need to change the code

46
00:01:59,430 --> 00:02:02,230
每当我们想尝试不同的模型结构时。
each time we want to try a different model architecture.

47
00:02:03,180 --> 00:02:05,353
正如我们之前所说，模型的配置
As we said before, the configuration of a model

48
00:02:05,353 --> 00:02:08,610
是包含所有必要信息的蓝图
is a blueprint that contains all the information necessary

49
00:02:08,610 --> 00:02:11,070
以创建模型结构。
to create the model architecture.

50
00:02:11,070 --> 00:02:12,750
例如，BERT 模型
For instance, the BERT model

51
00:02:12,750 --> 00:02:15,510
与 bert-base-cased 的 checkpoint 关联
associated with the bert-base-cased checkpoint

52
00:02:15,510 --> 00:02:19,710
有 12 层，隐藏大小为 768，
has 12 layers, a hidden size of 768,

53
00:02:19,710 --> 00:02:23,403
词汇量为 28,996。
and a vocabulary size of 28,996.

54
00:02:24,810 --> 00:02:26,670
一旦我们有了配置，
Once we have the configuration,

55
00:02:26,670 --> 00:02:28,890
我们可以创建一个具有相同结构的模型
we can create a model that has the same architecture

56
00:02:28,890 --> 00:02:32,160
作为我们的 checkpoint ，但是随机初始化的。
as our checkpoint but is randomly initialized.

57
00:02:32,160 --> 00:02:36,030
我们然后就可以像任何 TensorFlow 模型一样从头开始训练它。
We can then train it from scratch like any TensorFlow model.

58
00:02:36,030 --> 00:02:38,063
我们还可以更改配置的任何部分
We can also change any part of the configuration

59
00:02:38,063 --> 00:02:40,770
通过使用关键字参数。
by using keyword arguments.

60
00:02:40,770 --> 00:02:43,110
第二段代码实例化
The second snippet of code instantiates

61
00:02:43,110 --> 00:02:44,970
一个随机初始化的 BERT 模型
a randomly initialized BERT model

62
00:02:44,970 --> 00:02:46,983
有 10 层而不是 12 层。
with 10 layers instead of 12.

63
00:02:48,240 --> 00:02:51,360
训练或微调后保存模型非常容易。
Saving a model once it's trained or fine-tuned is very easy.

64
00:02:51,360 --> 00:02:53,880
我们只需要使用 save_pretrained 方法。
We just have to use the save_pretrained method.

65
00:02:53,880 --> 00:02:55,980
在这里，模型将保存在一个文件夹中
Here, the model will be saved in a folder

66
00:02:55,980 --> 00:02:59,463
在当前工作目录中命名为 my-bert-model。
named my-bert-model inside the current working directory.

67
00:03:00,480 --> 00:03:02,250
然后可以重新加载这样的模型
Such a model can then be reloaded

68
00:03:02,250 --> 00:03:04,500
使用 from_pretrained 方法。
using the from_pretrained method.

69
00:03:04,500 --> 00:03:06,600
要将其运行到 Hub 的项目模型，
To run it to a projects model to the Hub,

70
00:03:06,600 --> 00:03:08,350
查看推送（咕哝）视频。
check out the push (mumbles) video.

71
00:03:09,355 --> 00:03:12,188
（嘶嘶声）
(whooshing sound)