Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Converting T5 Large Models to ONNX Format and 8-bit Quantization with MLflow and Optimum

The Machine Learning Engineer via YouTube

Overview

Learn how to convert a T5 Large Model to ONNX format and perform 8INT quantization using the Huggingface Transformers Optimum library in this 48-minute technical video. Follow along with a practical demonstration of converting a fine-tuned text summarization model, with all steps tracked in MLFlow. Access the complete implementation through the provided Jupyter notebook to master model optimization techniques for improved deployment efficiency. Gain hands-on experience with MLOps practices while exploring the intersection of model conversion, quantization, and experiment tracking.

Syllabus

MLOps MLFlow: Convert to ONNX and quantize to 8Int with Optimum #datascience #machinelearning

Taught by

The Machine Learning Engineer

Reviews

Start your review of Converting T5 Large Models to ONNX Format and 8-bit Quantization with MLflow and Optimum

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.