1
00:00:00,468 --> 00:00:03,051
（欢快的音乐）
(upbeat music)

2
00:00:04,050 --> 00:00:05,910
- [Instructor] 在本视频中，我们将回顾
- [Instructor] In this video, we're going to go over

3
00:00:05,910 --> 00:00:08,013
HuggingFace Model Hub 导航。
the HuggingFace Model Hub navigation.

4
00:00:10,140 --> 00:00:13,260
这是 huggingface.co 登陆页面。
This is the huggingface.co landing page.

5
00:00:13,260 --> 00:00:16,020
要访问 Model Hub，请在右上角
To access the Model Hub, click on the Models tab

6
00:00:16,020 --> 00:00:17,463
单击 Models 选项卡。
in the upper right corner.

7
00:00:18,960 --> 00:00:21,030
你会看到这个网页界面，
You should be facing this web interface,

8
00:00:21,030 --> 00:00:23,193
它被分为几个部分。
which can be split into several parts.

9
00:00:24,480 --> 00:00:26,790
在左侧，你会找到类别 (category)，
On the left, you'll find categories,

10
00:00:26,790 --> 00:00:29,090
你可以使用它来自定义模型搜索。
which you can use to tailor your model search.

11
00:00:29,970 --> 00:00:32,970
第一类是任务 (tasks)。
The first category is the tasks.

12
00:00:32,970 --> 00:00:36,660
hub 上的模型可用于各种各样的任务。
Models on the hub may be used for a wide variety of tasks.

13
00:00:36,660 --> 00:00:39,030
这些包括自然语言处理任务，
These include natural language processing tasks,

14
00:00:39,030 --> 00:00:41,670
比如问答或者文本分类，
such as question answering or text classification,

15
00:00:41,670 --> 00:00:43,773
但它不仅限于 NLP。
but it isn't only limited to NLP.

16
00:00:44,850 --> 00:00:47,790
其他领域的其他任务也可用，
Other tasks from other fields are also available,

17
00:00:47,790 --> 00:00:50,340
例如计算机视觉的图像分类，
such as image classification for computer vision,

18
00:00:50,340 --> 00:00:52,683
或语音的自动语音识别。
or automatic speech recognition for speech.

19
00:00:54,840 --> 00:00:57,870
第二类是库 (Library)。
The second category is the libraries.

20
00:00:57,870 --> 00:01:00,990
hub 上的模型通常共享三个主要框架之一，
Models on the hub usually share one of three backbones,

21
00:01:00,990 --> 00:01:03,900
PyTorch、TensorFlow 或 JAX。
PyTorch, TensorFlow, or JAX.

22
00:01:03,900 --> 00:01:07,503
但是，也存在其他主干，例如 rust 或 ONNX。
However, other backbones, such as rust or ONNX also exist.

23
00:01:09,540 --> 00:01:11,850
最后，这个选项卡也可以
Finally, this tab can also be used

24
00:01:11,850 --> 00:01:15,123
指定模型来自哪个高级框架。
to specify from which high-level framework the models comes.

25
00:01:16,140 --> 00:01:19,260
这包括 Transformers ，但也不仅仅是这些。
This includes Transformers, but it isn't limited to it.

26
00:01:19,260 --> 00:01:21,060
Model Hub 用于托管
The Model Hub is used to host

27
00:01:21,060 --> 00:01:22,920
许多不同的框架模型，
a lot of different frameworks models,

28
00:01:22,920 --> 00:01:24,600
我们正在积极寻求
and we're actively looking to host

29
00:01:24,600 --> 00:01:25,893
支持其他框架模型。
other frameworks models.

30
00:01:28,530 --> 00:01:31,890
第三类是数据集 (Datasets) 选项卡。
The third category is the datasets tab.

31
00:01:31,890 --> 00:01:35,070
从此选项卡中选择数据集
Selecting a dataset from this tab means filtering the models

32
00:01:35,070 --> 00:01:37,683
意味筛选在特定数据集上训练的模型。
so that they were trained on that specific dataset.

33
00:01:39,180 --> 00:01:42,300
第四类是语言 (Language) 选项卡。
The fourth category is the languages tab.

34
00:01:42,300 --> 00:01:43,800
从此选项卡中选择一种语言
Selecting a language from this tab

35
00:01:43,800 --> 00:01:45,990
意味着筛选模型以便它们适配
means filtering the models so that they handle

36
00:01:45,990 --> 00:01:47,090
所选的语言。
the language selected.

37
00:01:48,600 --> 00:01:51,750
最后，最后一个类别允许选择模型之间
Finally, the last category allows to choose the license

38
00:01:51,750 --> 00:01:53,313
共享的许可证 (license)。
with which the model is shared.

39
00:01:56,700 --> 00:01:58,770
在右侧，你可以在 Model Hub　
On the right, you'll find the models available

40
00:01:58,770 --> 00:02:00,480
找到可用的模型。
on the Model Hub.

41
00:02:00,480 --> 00:02:03,750
默认情况下，模型按下载排序。
The models are ordered by downloads by default.

42
00:02:03,750 --> 00:02:04,890
单击模型时，
When clicking on a model,

43
00:02:04,890 --> 00:02:07,230
你可以看到它的模型卡。
you should be facing its model card.

44
00:02:07,230 --> 00:02:09,990
模型卡包含有关模型的信息，
The model card contains information about the model,

45
00:02:09,990 --> 00:02:13,263
它的描述、预期用途、限制和偏差。
its description, intended use, limitations and biases.

46
00:02:14,310 --> 00:02:17,580
它还可以展示与如何使用模型相关的代码片段，
It can also show code snippets on how to use the model,

47
00:02:17,580 --> 00:02:20,070
以及任何相关信息；
as well as any relevant information;

48
00:02:20,070 --> 00:02:22,080
训练过程，数据处理，
training procedure, data processing,

49
00:02:22,080 --> 00:02:24,213
评估结果或版权。
evaluation results or copyrights.

50
00:02:25,710 --> 00:02:28,350
此信息对于要使用的模型至关重要。
This information is crucial for the model to be used.

51
00:02:28,350 --> 00:02:30,360
制作得越好的模型卡，
The better crafted a model card is,

52
00:02:30,360 --> 00:02:33,270
越方便其他用户在他们的应用程序中
the easier it will be for other users to leverage your model

53
00:02:33,270 --> 00:02:34,443
利用你的模型。
in their applications.

54
00:02:35,820 --> 00:02:38,553
模型卡右侧是 inference API。
On the right of the model card is the inference API.

55
00:02:39,540 --> 00:02:41,040
可以使用此 interence API
This inference API can be used

56
00:02:41,040 --> 00:02:43,290
直接玩模型。
to play with the model directly.

57
00:02:43,290 --> 00:02:45,690
随意修改文字，点击 compute
Feel free to modify the text and click on compute

58
00:02:45,690 --> 00:02:48,140
看看模型对你的输入有何反应。
to see how would the model behave to your inputs.

59
00:02:50,370 --> 00:02:53,013
屏幕顶部是模型标签。
At the top of your screen lies the model tags.

60
00:02:53,850 --> 00:02:56,550
这些包括模型任务，以及任何其他标签
These include the model task, as well as any other tag

61
00:02:56,550 --> 00:02:59,200
这与我们刚才看到的类别相关。
that is relevant to the categories we have just seen.

62
00:03:01,320 --> 00:03:04,410
Files and versions 选项卡显示
The Files and versions tab displays the architecture

63
00:03:04,410 --> 00:03:06,213
模型仓库的架构。
of the repository of that model.

64
00:03:07,230 --> 00:03:10,920
在这里，我们可以看到定义此模型的所有文件。
Here, we can see all the files that define this model.

65
00:03:10,920 --> 00:03:13,650
你将看到 Git repository 的所有常用功能：
You'll see all usual features of a Git repository:

66
00:03:13,650 --> 00:03:15,093
可用的 branch，
the branches available,

67
00:03:17,160 --> 00:03:18,520
commit 历史
the commit history

68
00:03:20,760 --> 00:03:22,683
以及 commit diff。
as well as the commit diff.

69
00:03:25,740 --> 00:03:27,510
在模型卡的顶部
Three different buttons are available

70
00:03:27,510 --> 00:03:29,760
有三个不同的按钮可用。
at the top of the model card.

71
00:03:29,760 --> 00:03:31,170
第一个显示如何在代码中
The first one shows how to use

72
00:03:31,170 --> 00:03:33,093
使用 inference API。
the inference API programmatically.

73
00:03:35,910 --> 00:03:38,913
第二个展示了如何在 SageMaker 中训练这个模型。
The second one shows how to train this model in SageMaker.

74
00:03:42,870 --> 00:03:44,820
最后一个显示了如何在适当的库中
And the last one shows how to load that model

75
00:03:44,820 --> 00:03:46,860
加载该模型。
within the appropriate library.

76
00:03:46,860 --> 00:03:48,783
对于 BERT，这是 transformers。
For BERT, this is transformers.

77
00:03:50,208 --> 00:03:52,791
（欢快的音乐）
(upbeat music)