课程

Large Language Models (LLMs) 概念

基础技能水平

更新时间 2026年5月

通过我们的概念性课程，发掘 LLM 的全部潜力，涵盖 LLM 应用、训练方法、伦理考量和最新研究。

免费开始课程

TheoryArtificial Intelligence

2小时

15 视频

50 道练习

3,000 XP

100K+

成就证明

深受数千家公司学习者的喜爱

需要团队培训？

企业版试用

课程描述

探索大型语言模型

在本课程中，你将探索大型语言模型（LLMs）的世界，并了解它们如何重塑人工智能格局。你将探索推动 LLM 热潮的因素，例如深度学习革命、数据可用性和计算能力。

这门概念性课程将深入探讨大语言模型（LLM），以及它们如何通过真实案例彻底改变企业和日常生活，涵盖从金融到内容创作等多个领域。

揭开 LLM 和训练方法的奥秘

你将了解 LLM 的构建基础，包括自然语言处理技术、微调策略，以及零样本、少样本和多样本学习等学习技术。随着学习的深入，你将深入了解驱动 LLM 的前沿训练方法，包括下一个词预测、掩码语言建模和注意力机制。

探索 LLM 的关注点与注意事项

你还将探讨构建和训练 LLM 时的关键伦理与环境考量，例如训练数据和隐私问题。

当你完成这门课程时，你将了解如何在深入研究 LLM 领域最新成果的同时保持领先。你将探索未来的发展，重点关注模型可解释性、无监督偏差处理、计算效率以及增强创造力。

在本课程结束时，你将全面了解 LLM、它们的能力、应用以及引人入胜的挑战。

先决条件

Understanding Machine Learning

1

Introduction to Large Language Models (LLM)

The AI landscape is evolving rapidly, and Large Language Models (LLMs) are at the forefront of this evolution. This chapter examines how LLMs are advancing the development of human-like artificial intelligence and transforming industries through their numerous applications. You will explore the challenges and complexity associated with language modeling.

The rise of LLMs in the AI landscape

Definition of an LLM

LLMs in the AI landscape

AI vs. LLM applications

Real-world applications

Business applications

Multimodal applications

Automate data-driven tasks

Challenges of language modeling

What can a language model do?

Single vs. multi-task learning

2

Building Blocks of LLMs

This chapter emphasizes the novelty of LLMs and their emergent capabilities while outlining various NLP techniques for data preparation. You will learn the challenges of training LLMs and how fine-tuning can effectively address them. You will also understand how N-shot learning techniques enable efficient adaptation of pre-trained models when faced with limited labeled data.

Novelty of LLMs

Problem solving with LLMs

Traditional models vs. LLMs

Generalized overview of NLP

Data preparation

Text preprocessing and representation

Word embeddings over bag-of-words

Fine-tuning

Challenges in building LLMs

Adapt a pre-trained model

Pre-trained or fine-tuned?

Learning techniques

Fine-tune a model

N-shot learning

3

Training Methodology and Techniques

In this chapter, you will learn about the fundamental building blocks of training an LLM, such as pre-training techniques. You'll also gain an intuitive understanding of complex concepts like transformer architecture, including the attention mechanism. The chapter discusses an advanced fine-tuning technique and summarizes the training process to complete an LLM.

Building blocks to train LLMs

Masked language

Predict the next word

Building from scratch

Introducing the transformer

Relationships between distant words

Transformer components

Attention mechanisms

Focus of multi-head attention

Self vs. multi-head attention

Advanced fine-tuning

End-to-end training

Training, tuning & feedback

Building an LLM

4

Concerns and Considerations

In this chapter, we delve into the key considerations when training LLMs, such as large data availability, data quality, accurate labeling, and the implications of biased data. You will also examine various LLM risks like data privacy, ethical concerns, and environmental impact. Lastly, the chapter concludes by discussing emerging research areas and the evolving landscape of LLMs.

Data concerns and considerations

Is your model fair?

Un-biased and relevant

Customer service of a bank

Ethical and environmental concerns

Responsible use

Ethics and environment

Where are LLMs heading?

Creativity vs. efficiency

Analyzing literary works

Time to wrap-up

Large Language Models (LLMs) 概念

课程完成

获得成就证明

将此证书添加到您的 LinkedIn 档案、简历或履历中
在社交媒体和绩效评估中分享立即注册

加入超过19百万学习者，今天就开始Large Language Models (LLMs) 概念！

通过 DataCamp for Mobile 提升您的数据技能

随时随地通过我们的移动课程和每日 5 分钟编程挑战提升技能。