Published inTDS ArchiveHow Did Open Food Facts Fix OCR-Extracted Ingredients Using Open-Source LLMs?Delve into an end-to-end Machine Learning project to improve the quality of the Open Food Facts databaseOct 6, 20241Oct 6, 20241
DuckDB & Open Food Facts: the largest open food database in the palm of your hand π¦πExploit the power of DuckDB to explore the largest open database in the food market.Jul 21, 2024Jul 21, 2024
Published inTDS ArchiveParse Your Invoices with LayoutLM and Label StudioFine-tune LayoutLM on your invoices with the Transformers library, Label Studio, and AWS S3.Apr 16, 20246Apr 16, 20246
Published inTDS ArchiveScale your Machine Learning Projects with SOLID principlesHow to write code that scales and accelerates your work as a data scientist or machine learning engineer.Mar 12, 20248Mar 12, 20248
Published inTDS ArchiveBuild Machine Learning Pipelines with Airflow and Mlflow: Reservation Cancellation ForecastingLearn how to create reproducible and ready-for-production Machine Learning pipelines through a Senior Machine Learning assignmentJan 12, 20246Jan 12, 20246
Published inTDS ArchiveBuilding a Matching Tool to Help Start-Up Founders Find the Best Incubators: an End-to-Endβ¦A project walkthrough to propose the best incubators for start-up founders, using Python, Pinecone, FastAPI, Pydantic, and DockerNov 26, 2023Nov 26, 2023
Published inTowards AIWhy are AI Products Doomed to Fail?After one year of implementing AI features for various businesses, I share my perspective on the mistakes I see companies making with LLMsβ¦Nov 17, 202341Nov 17, 202341
Track your data with Data Version Control (DVC)A data tracking tool that works along Git to make your Machine Learning projects reproducible.Aug 27, 2023Aug 27, 2023
Fine-tune your LLM with AWS Sagemaker: build the best D&D assistant with generative AIA walkthrough on how to leverage Sagemaker to perform supervised fine-tuning on large language models.Aug 20, 20231Aug 20, 20231
Published inTowards AIFit Your LLM on a single GPU with Gradient Checkpointing, LoRA, and Quantization: a deep diveWhoever has ever tried to fine-tune a Large Language Model knows how hard it is to handle the GPU memory.Aug 3, 20231Aug 3, 20231