1-Transformer_models-9-End-of-chapter_quiz

中英文对照学习，效果更佳！
原课程链接：https://huggingface.co/course/chapter1/10?fw=pt

End-of-chapter quiz

章末测验

Ask a Question

问一个问题

This chapter covered a lot of ground! Don’t worry if you didn’t grasp all the details; the next chapters will help you understand how things work under the hood.

这一章涵盖了很多领域！如果您没有掌握所有细节，请不要担心；下一章将帮助您了解事情是如何在幕后运行的。

First, though, let’s test what you learned in this chapter!

不过，首先让我们测试一下您在本章中学到了什么！

  1. Explore the Hub and look for the roberta-large-mnli checkpoint. What task does it perform?

Summarization

探索Hub，寻找`roberta-Large-mnli‘检查点。它执行什么任务？摘要

Text classification

文本分类

Text generation

文本生成

  1. What will the following code return?
1
2
3
4
from transformers import pipeline

ner = pipeline("ner", grouped_entities=True)
ner("My name is Sylvain and I work at Hugging Face in Brooklyn.")

It will return classification scores for this sentence, with labels “positive” or “negative”.

下面的代码将返回什么？它将返回该句子的分类分数，标签为“积极”或“消极”。

It will return a generated text completing this sentence.

它将返回完成此句子的生成文本。

It will return the words representing persons, organizations or locations.

它将返回代表个人、组织或位置的单词。

  1. What should replace … in this code sample?
1
2
3
4
from transformers import pipeline

filler = pipeline("fill-mask", model="bert-base-cased")
result = filler("...")

This has been waiting for you.

什么应该取代…在这个代码样例中？这一直在等着您。

This [MASK] has been waiting for you.

这个[面具]一直在等你。

This man has been waiting for you.

这个人一直在等你。

  1. Why will this code fail?
1
2
3
4
from transformers import pipeline

classifier = pipeline("zero-shot-classification")
result = classifier("This is a course about the Transformers library")

This pipeline requires that labels be given to classify this text.

为什么这个代码会失败？这个管道需要给出标签来对这个文本进行分类。

This pipeline requires several sentences, not just one.

这条管道需要几句话，而不是一句话。

The 🤗 Transformers library is broken, as usual.

像往常一样，🤗Transformer的库被破坏了。

This pipeline requires longer inputs; this one is too short.

这条管道需要更长的输入；这条管道太短了。

  1. What does “transfer learning” mean?

Transferring the knowledge of a pretrained model to a new model by training it on the same dataset.

转移学习是什么意思？通过在相同的数据集上训练，将预先训练好的模型的知识转移到新模型上。

Transferring the knowledge of a pretrained model to a new model by initializing the second model with the first model’s weights.

通过用第一模型的权重来初始化第二模型，将预先训练的模型的知识转移到新模型。

Transferring the knowledge of a pretrained model to a new model by building the second model with the same architecture as the first model.

通过构建具有与第一模型相同的体系结构的第二模型，将预先训练的模型的知识转移到新模型。

  1. True or false? A language model usually does not need labels for its pretraining.

True

对还是错？语言模型通常不需要标签来进行预训练。

False

错误

  1. Select the sentence that best describes the terms “model”, “architecture”, and “weights”.

If a model is a building, its architecture is the blueprint and the weights are the people living inside.

选择最能描述“模型”、“建筑”和“重量”这三个术语的句子。如果一个模型是一座建筑，它的建筑就是蓝图，而重量就是住在里面的人。

An architecture is a map to build a model and its weights are the cities represented on the map.

建筑是一张构建模型的地图，它的权重是地图上表示的城市。

An architecture is a succession of mathematical functions to build a model and its weights are those functions parameters.

体系结构是一系列用于构建模型的数学函数，其权重是这些函数参数。

您会使用以下哪种类型的模型来完成生成文本的提示？编码器模型

  1. Which of these types of models would you use for completing prompts with generated text?

An encoder model

一种解码器模型

A decoder model

一种序列到序列模型

A sequence-to-sequence model

您会使用哪种类型的模型来汇总文本？编码器模型

  1. Which of those types of models would you use for summarizing texts?

An encoder model

一种解码器模型

A decoder model

一种序列到序列模型

A sequence-to-sequence model

您会使用哪种类型的模型来根据特定标签对文本输入进行分类？编码器模型

  1. Which of these types of models would you use for classifying text inputs according to certain labels?

An encoder model

一种解码器模型

A decoder model

一种序列到序列模型

A sequence-to-sequence model

在一个模型中观察到的偏差可能有什么来源？该模型是预先训练好的模型的微调版本，它从这个模型中获取它的偏差。

  1. What possible source can the bias observed in a model have?

The model is a fine-tuned version of a pretrained model and it picked up its bias from it.

对该模型进行训练的数据是有偏见的。

The data the model was trained on is biased.

该模型优化的指标是有偏见的。

The metric the model was optimizing for is biased.