Philipp Schmid 6/30/2022

Optimizing Transformers with Hugging Face Optimum

Read Original

This technical tutorial demonstrates how to optimize a DistilBERT model using Hugging Face Optimum and ONNX Runtime. It covers converting a model to ONNX, applying graph optimizations and dynamic quantization, and evaluating performance gains in latency while preserving accuracy. The guide includes steps to push and load quantized models from the Hugging Face Hub.

Optimizing Transformers with Hugging Face Optimum

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser