|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/ai-engineering-with-modal/
课程评论：没有评论
课程名称：使用Modal进行AI工程 课程概述： 欢迎参加《使用Modal进行AI工程》课程，这是一本实践指南，帮助您使用Python构建和部署高质量的AI系统。请注意，该课程尚未完成，新的内容将每周添加，因此当前价格较低，未来随着内容的增加将逐步上涨。本课程旨在改变您的工作流程，您将不再需要复杂的YAML文件、Docker文件和云配置面板，而是直接在Python代码中定义整个AI基础设施，包括自定义容器映像、按需GPU、持久存储和可扩展的Web端点。 本课程为项目驱动型，您将不仅学习理论知识，还将从头开始构建和部署实际的AI应用程序。主要项目包括： 1. 可扩展的语音识别管道：构建一个强大的系统，使用GPU加速的自动语音识别模型并行转录长音频文件。 2. 精细调优的分类模型：在自定义数据集上微调现代变换器模型（ModernBERT），用于文本分类任务，并将其部署为实时API。 3. 高吞吐量的LLM端点：使用vLLM启动与OpenAI兼容的强大大型语言模型API（如Qwen或Gemma），实现快速推断。 4. 使用Modal Sandbox构建编码代理：创建一个代码解释器代理，结合LLM和安全的云环境，执行任意Python代码。 5. 更多内容即将推出！ 课程结束时，您将能够自信地将任何AI模型从本地脚本转化为准备生产的可扩展云原生应用程序。 您将掌握的内容： - Modal基础：从零到英雄，掌握Modal的核心概念，远程并行运行函数。 - 基础设施即代码：使用Python构建自定义容器图像，预留强大的GPU（A100s、H100s），管理CPU/内存以及使用持久卷。 - 端到端AI流程：将复杂的AI任务如模型训练、批处理和推断结构化为清晰可管理的Modal应用程序。 - 大规模模型微调：利用按需GPU运行和管理现代变换器模型的微调任务。 - 轻松部署：仅需少量代码即可将训练后的模型和LLM部署为快速、可扩展的Web API。 本课程适合任何熟悉Python并对AI感兴趣的人士。
NOTE: This course is not complete and new content is being added weekly. Therefore the course is cheaper at the moment and the cost will increase over time as hours of more content is added.Welcome to AI Engineering with Modal, your hands-on guide to building and deploying production-grade AI systems with nothing but Python. This course is designed to transform your workflow. We'll ditch the complex YAML files, Dockerfiles, and cloud configuration panels. Instead, you'll learn how to define your entire AI infrastructure-from custom container images and on-demand GPUs to persistent storage and scalable web endpoints-directly within your Python code.This is a project-based course where you won't just learn the theory; you'll build and deploy real-world AI applications from the ground up:A Scalable ASR Pipeline: Build a robust system to transcribe long audio files in parallel using a GPU-accelerated Automatic Speech Recognition model.A Fine-Tuned Classification Model: Fine-tune a modern transformer model (ModernBERT) on a custom dataset for a text classification task and deploy it as a live API.A High-Throughput LLM Endpoint: Launch an OpenAI-compatible API for a powerful Large Language Model (like Qwen or Gemma) using vLLM for blazingly fast inference.Building a Coding Agent with Modal Sandboxes: Build your own code interpreter Agent with an LLM and an isolated secure cloud environment for executing arbitrary python code. And More To Come!By the end of this course, you'll be able to confidently take any AI model from a local script to a scalable, cloud-native application ready for production.What you will master:Modal Fundamentals: Go from zero to hero with Modal's core concepts, running functions remotely and in parallel.Infrastructure as Code: Build custom container images, reserve powerful GPUs (A100s, H100s), manage CPU/memory, and use persistent Volumes-all in Python.End-to-End AI Pipelines: Structure complex AI tasks like model training, batch processing, and inference into clean, manageable Modal applications.Model Fine-Tuning at Scale: Leverage on-demand GPUs to run and manage fine-tuning jobs for modern transformer models.Effortless Deployment: Deploy your trained models and LLMs as fast, scalable web APIs with just a few lines of code.And More!This course is for anyone familiar with Python and interested in AI.
