|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/genai-llm-aws
课程评论：没有评论
课程总结：AWS上的GenAI和LLMs 本课程旨在教授如何在生产环境中使用AWS服务（如Amazon Bedrock）部署和管理大型语言模型（LLMs）。通过本课程的学习，您将掌握以下技能： - 根据应用需求选择合适的LLM架构和模型。 - 利用自动扩展组、竞价实例和容器编排来优化LLM在AWS上的成本、性能和可扩展性。 - 监控和记录LLM的指标，以检测问题并不断提高模型质量。 - 构建可靠的系统。 课程大纲涵盖以下模块： 1. **AWS上AI开发入门** - 学习如何设置Rust开发环境，利用AWS SDK for Rust，并使用Rust构建AWS Lambda函数。 2. **从CodeWhisperer到提示工程的AI配对编程** - 了解如何指导CodeWhisperer编写代码，掌握链式思维提示技巧以让模型自我解释，构建CLI工具和bash函数，并利用CodeWhisperer CLI自动化任务，实现高效的AI编程。 3. **Amazon Bedrock** - 学习Amazon Bedrock的功能，并进行模型评估和定制应用。 4. **项目挑战** - 通过挑战性的项目，您将有机会在新的上下文中应用之前模块中所学的概念，进一步巩固学习效果。 通过本课程的学习，您将能够熟练应用AWS服务来管理和优化大型语言模型，为实现AI应用打下坚实的基础。
Name:Getting Started with Developing on AWS for AI
Description:This module, you will learn how to set up a Rust development environment, utilize the AWS SDK for Rust, and build AWS Lambda functions with Rust.
Name:AI Pair Programming from CodeWhisperer to Prompt Engineering
Description:CodeWhisperer writes code. You learn to guide it. Large language models crunch data, spit out content. Chain-of-thought prompts make models explain themselves. Craft prompts, shape outputs. Build CLI tools, bash functions. Use CodeWhisperer CLI to automate tasks. Fast, efficient coding with AI.
Name:Amazon Bedrock
Description:This module, learn Amazon Bedrock capabilities. Apply through model evaluations and customizations.
Name:Project Challenges
Description:In this module, you will challenge yourself to apply the concepts covered in the previous module and challenge yourself to apply what you learned in a new context.
This course will teach you how to deploy and manage large language models (LLMs) in production using AWS services like Amazon Bedrock. By the end of the course, you will know how to: Choose the right LLM architecture and model for your application using services. Optimize cost, performance and scalability of LLMs on AWS using auto-scaling groups, spot instances and container orchestration Monitor and log metrics from your LLM to detect issues and continuously improve quality Build reliable and s
