Open in app

Sign In

Write

Sign In

Julien Simon
Julien Simon

6.7K Followers

Home

About

Pinned

Next public talks

Here’s the current list of public events I’ll be speaking at. I will keep it as up-to-date as possible! I’m always open to speaking at public events (online or in-person). I’m also happy to explore opportunities for in-house talks. Don’t hesitate to get in touch with details at julsimon@huggingface.co. March…

3 min read

3 min read


Feb 24

Video — Transformer training shootout: AWS Trainium vs. NVIDIA A10G

In this video, I compare the cost-performance of AWS Trainium, a new custom chip designed by AWS, with NVIDIA A10G GPUs. I first launch a trn1.32xlarge instance (16 Trainium chips) and a g5.48xlarge (8 A10Gs). Then, I run a natural language processing job, fine-tuning the BERT Large model on the full Yelp review datatset. I use the BF16 data format with the maximum sequence length supported by the model (512). The results? The Trainium job is 5x faster. As the trn1 instance is only 30% more expensive, this is a huge improvement in cost-performance!

Hugging Face

1 min read

Hugging Face

1 min read


Feb 23

Video: Training Transformers with AWS Trainium and the Hugging Face Neuron AMI

In this video, I show you how to accelerate Transformer training with AWS Trainium, a new custom chip designed by AWS, and the brand new Hugging Face Neuron Amazon Machine Image (AMI). First, I walk you through the setup of an Amazon EC2 trn1.32xlarge instance, equipped with 16 Trainium chips. Then, I run a natural language processing job, accelerating a BERT model to classify the Yelp review datatset on 32 Neuron cores.

Deep Learning

1 min read

Deep Learning

1 min read


Feb 20

Webinar: How Witty Works leverages Hugging Face to scale inclusive language

Witty Works builds a digital writing assistant for inclusive language. We discussed text classification, few-shot learning, the benefits of the SetFit library, and how Hugging Face helped get to production quicker :)

NLP

1 min read

NLP

1 min read


Feb 10

Video: Fast and accurate language identification with Hugging Face and Intel OpenVINO

Hyperproductive ML with Hugging Face in action! With just a few lines of code, here’s how I trained a highly accurate language identification model, and then optimized its latency 3x with Optimum Intel and Openvino 😎

Deep Learning

1 min read

Deep Learning

1 min read


Feb 7

3 new videos: Intel Sapphire Rapids inference, few-shot learning with SetFit, and semantic search on images and videos with BridgeTower

Not one, but three new Hugging Face videos today :) Learn and share! In this video, you will learn how to accelerate PyTorch inference with an Intel Sapphire Rapids server running on AWS. Working with popular Hugging Face transformers implemented with PyTorch, we’ll first measure their performance on an…

Transformers

1 min read

Transformers

1 min read


Jan 17

Demo: question answering on tabular data

Tabular data is everywhere, from spreadsheets to tables embedded in text documents. In this Hugging Face Space, you can use the Google TAPAS and Microsoft TAPEX models to ask questions in natural language on CSV data. Give it a try and let me know what you think :) ✅ Space…

NLP

1 min read

Demo: question answering on tabular data
Demo: question answering on tabular data
NLP

1 min read


Jan 16

Demo: the battle of the image classifiers

The Hugging Face hub hosts 1,700+ image classification models. I’ve picked the top ones from Google, Meta, Microsoft, NVIDIA and Humphrey Shi. All of them have been fine-funed on the ImageNet-1k dataset, which makes it easy to compare their performance on your images. Enjoy! Space: https://huggingface.co/spaces/juliensimon/battle_of_image_classifiers

Deep Learning

1 min read

Demo: the battle of the image classifiers
Demo: the battle of the image classifiers
Deep Learning

1 min read


Jan 16

Demo: audio classification with the Audio Spectrogram Transformer

Multi-modal transformers are rising fast. A great example is the Audio Spectrogram Transformer, an audio classification model that was just added to the Hugging Face Transformers library. This model first creates a spectrogram image of an audio clip and then classifies the image with a Vision Transformer model. Amazing results! ✅ Spaces demo: https://huggingface.co/spaces/juliensimon/keyword-spotting ✅ Model: https://huggingface.co/MIT/ast-finetuned-speech-commands-v2 ✅ Paper: https://arxiv.org/abs/2104.01778

Deep Learning

1 min read

Demo: audio classification with the Audio Spectrogram Transformer
Demo: audio classification with the Audio Spectrogram Transformer
Deep Learning

1 min read


Jan 16

Demo: question answering on HTML documents

What if you could ask questions on HTML documents, without having to convert them to plain text first? Well, that’s exactly the purpose of the Microsoft MarkupLM: just grab a page and ask a question. I’ve built a Hugging Face Space to let you experiment with any live URL. I…

Transformers

1 min read

Demo: question answering on HTML documents
Demo: question answering on HTML documents
Transformers

1 min read

Julien Simon

Julien Simon

6.7K Followers

Chief Evangelist, Hugging Face (https://huggingface.co)

Following
  • Adrian Hornsby

    Adrian Hornsby

  • Netflix Technology Blog

    Netflix Technology Blog

  • Jeff Barr

    Jeff Barr

  • Michel de Cryptadamus

    Michel de Cryptadamus

  • Less Wright

    Less Wright

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech