YoVDO

Shopify's Ray-Powered Approach to Multimodal AI in E-commerce

Offered By: Anyscale via YouTube

Tags

E-commerce Courses Shopify Courses Generative AI Courses Multimodal AI Courses Fine-Tuning Courses Vision-Language Models Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore Shopify's innovative approach to implementing multimodal Large Language Models (LLMs) at scale in this breakout session from Ray Summit 2024. Dive into the experiences shared by Niklas Itanen and Kshetrajna Raghavan as they detail Shopify's process of fine-tuning and deploying large vision language models in a production environment. Gain insights into how Shopify integrates Ray alongside other open-source tools to handle the complexities of multimodal LLMs at their operational scale. Follow a comprehensive walkthrough of a specific generative AI use case, demonstrating the effective utilization of Ray in conjunction with other tools to power sophisticated AI applications in high-demand, real-world e-commerce scenarios. Benefit from this 31-minute presentation to understand how teams can leverage Ray for implementing advanced AI solutions in production environments.

Syllabus

Shopify's Ray-Powered Approach to Multimodal AI in E-commerce | Ray Summit 2024


Taught by

Anyscale

Related Courses

Mastering Google's PaliGemma VLM: Tips and Tricks for Success and Fine-Tuning
Sam Witteveen via YouTube
Fine-tuning PaliGemma for Custom Object Detection
Roboflow via YouTube
Florence-2: The Best Small Vision Language Model - Capabilities and Demo
Sam Witteveen via YouTube
Fine-tuning Florence-2: Microsoft's Multimodal Model for Custom Object Detection
Roboflow via YouTube
OpenVLA: An Open-Source Vision-Language-Action Model - Research Presentation
HuggingFace via YouTube