|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/1z0-1127-24-oracle-cloud-infra-gen-ai-prof-practice-exam/
课程评论：没有评论
课程名称：1Z0-1127-24 Oracle Cloud Infra Gen AI 实践考试 课程概述： 本课程旨在帮助有志于成为人工智能专业人士的学员，深度了解生成式人工智能（Generative AI）在Oracle云基础设施（OCI）中的应用。通过这一全面的实践考试，学员将掌握大型语言模型（LLMs）的基本原理和高级概念，学习如何利用OCI的前沿生成式AI服务进行开发和应用。 课程内容涵盖LLMs的核心原理，包括其架构和提示工程的细节。学员将了解LLMs的微调过程，并深入探索专门的模型，如代码模型、多模态模型和语言代理。接着，课程将重点介绍OCI的生成式AI服务，教您如何利用预训练的基础模型完成生成、摘要和嵌入等任务。学员还将学习如何创建专用的AI集群以进行微调和推理，并掌握使用自定义数据集对基础模型进行微调的方法。此外，课程将讲解OCI生成式AI的安全架构，以及如何创建和使用模型端点进行推理。 课程的高潮部分是实践应用，学员将使用OCI的生成式AI服务构建LLM应用程序。内容包括检索增强生成（RAG）、向量数据库概念和语义搜索的理解。学员将学习构建Lang Chain模型、提示、记忆和链，并将其整合到一个功能完整的LLM应用中。最后，您将能够追踪、评估和部署您的LLM应用，确保其达到高标准的性能和可靠性。 通过本课程，学员将全面掌握生成式AI的使用，加深对OCI服务的理解，为未来在AI领域的职业发展打下坚实基础。
Unlock the power of Generative AI with Oracle Cloud Infrastructure (OCI) in this comprehensive Practice Exam designed for aspiring AI professionals. This Practice Exam provides a deep dive into the fundamentals and advanced concepts of Large Language Models (LLMs), equipping you with the knowledge and skills to leverage OCI's cutting-edge Generative AI services. From understanding LLM architectures to building and deploying sophisticated AI applications, this course covers it all.We begin by exploring the core principles of LLMs, including their architectures and the nuances of prompt engineering. You will gain insights into LLM fine-tuning and delve into specialized models such as code models, multi-modal models, and language agents.Next, we focus on the OCI Generative AI service. Learn how to utilize pretrained foundational models for tasks such as generation, summarization, and embedding. Discover how to create dedicated AI clusters for fine-tuning and inference and master the process of fine-tuning base models with custom datasets. You will also explore the security architecture of OCI Generative AI and how to create and use model endpoints for inference.The course culminates with practical applications, where you will build an LLM application using OCI Generative AI services. Understand Retrieval Augmented Generation (RAG), vector database concepts, and semantic search. Learn to construct Lang Chain models, prompts, memory, and chains, and integrate them into a functional LLM application. Finally, you will trace, evaluate, and deploy your LLM application, ensuring it meets the highest standards of performance and reliability.
