PinnedJulien SimonNext public talksHere’s the current list of public events I’ll be speaking at. I will keep it as up-to-date as possible!4 min read·May 12, 2022--1--1
Julien SimonMigrating from OpenAI models to Hugging Face modelsIn this video, I show how you can easily migrate your applications from OpenAI models to Hugging Face open-source models.1 min read·3 days ago----
Julien SimonVideo: Llama 3 on Amazon SageMakerIn this video, I walk you through the simple process of deploying a Llama 3 8B model with Amazon SageMaker.1 min read·Apr 18, 2024----
Julien SimonVideos: Deploying Hugging Face models on Google CloudNot one, not two, but THREE video walkthroughs showing you how to easily deploy Hugging Face models on Google Cloud Platform:1 min read·Apr 9, 2024----
Julien SimonVideo: Enterprise AI with the Hugging Face Enterprise HubCurious how the Hugging Face Enterprise hub, an enterprise-ready version of the world’s leading AI platform, can help your organization…1 min read·Apr 2, 2024----
Julien SimonVideo: Deploying Hugging Face models with Amazon SageMaker and AWS Inferentia2In this video, I walk you through the simple process of deploying a Hugging Face large language model on AWS, with Amazon SageMaker and the…1 min read·Mar 29, 2024----
Julien SimonAnnouncing the Hugging Face / AWS roadshowUS friends, the Hugging Face / Amazon Web Services (AWS) roadshow is three weeks away.1 min read·Mar 20, 2024----
Julien SimonVideo — Deep dive: model mergingModel merging is an increasingly popular technique that makes it possible to add or remove capabilities to transformer models, without the…1 min read·Mar 18, 2024----
Julien SimonVideo — Deep Dive: Optimizing LLM inferenceOpen-source LLMs are great for conversational applications, but they can be difficult to scale in production and often deliver latency and…1 min read·Mar 11, 2024----
Julien SimonVideo — Deep Dive: Quantizing Large Language ModelsQuantization is an excellent technique to compress Large Language Models (LLM) and accelerate their inference.1 min read·Mar 6, 2024----