Budapest ML Forum 2022 - Főoldal - Budapest ML Forum 2022 About the conference The Budapest ML Forum is a two-day international conference in hybrid format on data science…budapestml.hu

In this video, I use AutoTrain, an AutoML product designed by Hugging Face, to train a multi-class classification model on tabular data (the PetFinder dataset from Kaggle). Original dataset: https://www.kaggle.com/competitions/petfinder-adoption-prediction/ Dataset on the hub: https://huggingface.co/datasets/juliensimon/autotrain-data-petfinder-demo Model on the hub: https://huggingface.co/juliensimon/autotrain-tabular-demo-762523398

This video is a technical deep dive on the demo presented in https://youtu.be/I_hqzdqQ5vE, where I run multilingual voice queries on financial documents, using two state of the art Transformer models for speech to text and semantic search in less than 100 lines of Python: — Dataset preparation, based on SEC filings downloaded with an AWS SDK. See https://youtu.be/SU1L6f0N6iw for details. — Experimentation in a Jupyter notebook, available at https://gitlab.com/juliensimon/huggingface-demos/-/tree/main/voice-queries

This 5-minute video is for anyone curious about state-of-the-art Machine Learning, developer or not :) I introduce you to the value of Transformers and Hugging Face, and how they bring Software Engineering agility to Machine Learning. To prove my point, I run a web app running multilingual voice queries on financial documents, in less than 100 lines of Python. You can run it too at https://huggingface.co/spaces/juliensimon/voice-queries/

It’s that time of the year again! AWS re:Invent 2021 is over, and it’s time to update my maps once again: Overall map for all AI and ML services, Model deployment map, SageMaker map. As usual, you’ll find the latest XMind and high-resolution PNG versions on Gitlab: https://gitlab.com/juliensimon/awsmlmap. Enjoy, and please let me know if I forgot anything.

In this video, I show you how to: easily download SEC filings with a bespoke AWS SDK, process and break down filings into individual text sections, extract insights using Hugging Face models for sentiment analysis, emotion detection, and summarization. ⭐️⭐️⭐️ Don’t forget to subscribe to be notified of future videos ⭐️⭐️⭐️ Blog post: https://aws.amazon.com/blogs/machine-learning/create-a-dashboard-with-sec-text-for-financial-nlp-in-amazon-sagemaker-jumpstart/

In this video, I start from an Amazon research paper and its companion dataset for detection of counterfactual text. Using the Hugging Face open source libraries, I use the reproduce the training job described in the paper, and I compare my metrics to the ones reported in the paper. Did I do better? Watch this video to find out :) ⭐️⭐️⭐️ Don’t forget to subscribe to be notified of future videos ⭐️⭐️⭐️

In this video, I demo SageMaker Studio Lab, a managed Jupyter notebook service running on AWS. Using a CPU runtime, I first run a simple Hugging Face example based on the Pipeline API. Then, I switch to a GPU runtime and run a fine-tuning example on DistilBERT with the Trainer API. Along the way, I inspect the infrastructure resources available in both runtimes. I also show you how to create your own conda environment to keep your dependencies neatly organized.

At long last, Amazon SageMaker supports serverless endpoints. — In this video, I demo this newly launched capability, named Serverless Inference. Starting from a pre-trained DistilBERT model on the Hugging Face model hub, I fine-tune it for sentiment analysis on the IMDB movie review dataset. Then, I deploy the model to a serverless endpoint, and I run multi-threaded benchmarks with short and long token sequences. Finally, I plot latency numbers and compute latency quantiles.