Eivind Kjosbakken

Learn how to fine-tune ModernBERT and create augmentations of text samples Eivind Kjosbakken · Follow Published in Towards Data Science · 8 min read · 9 hours ago — In this article, I discuss how you can implement and fine-tune the new ModernBERT text model. Furthermore, I use the model on a classic text classification task and show you how you can utilize synthetic data to improve the model’s performance. In this article, I discuss

Create a machine-learning-based search into legal decisions Eivind Kjosbakken · Follow Published in Towards Data Science · 10 min read · 11 hours ago — In this article, I describe how I created an application to search for supreme court decisions in Norway. This application is a useful tool for quickly gaining insights into decisions made on different topics, which is especially interesting if you want to learn the Supreme Court’s stance on particular subjects.

Learn how you can develop an application to search emails using RAG Eivind Kjosbakken · Follow Published in Towards Data Science · 13 min read · 3 hours ago — In this article, I will show you how you can develop the MailDiscoverer application to search Gmail emails using RAG. First, I will show you how to set up the authentication pipeline to access user’s emails (if consent is given). The emails are then embedded

Learn how to utilize Meta’s new SAM 2 model to segment anything Eivind Kjosbakken · Follow Published in Towards Data Science · 9 min read · 2 hours ago — Segment Anything Model 2 is Meta’s latest image segmentation model, capable of detecting and marking objects in images and code. This article will show you how to download and utilize the model and review the model and its capabilities. Using image segmentation models is exciting

Learn about TinyLlama, a smaller language model capable of a variety of complex tasks with a small amount of compute Eivind Kjosbakken · Follow Published in Towards Data Science · 10 min read · 12 hours ago — TinyLlama is an open-source project that trains a small language model of around 1.1B parameters. The project aims to have a language model capable of performing tasks a full LLM like Llama 2 can achieve but with

Leverage the power of the mPLUG-Owl document understanding model to ask questions about your documents Eivind Kjosbakken · Follow Published in Towards Data Science · 9 min read · 21 hours ago — This article will discuss the Alibaba document understanding model, recently released with model weights and datasets. It is a powerful model capable of performing various tasks such as document question answering, extracting information, and document embedding, making it a helpful tool when

Learn how you can improve your graphs for machine-learning tasks. Eivind Kjosbakken · Follow Published in Towards Data Science · 14 min read · 1 hour ago — Graphs defined by topological information are helpful in many machine-learning scenarios. They can be used for community detection, node influence, classification, and other tasks. The performance a machine-learning mode can achieve on these tasks will strongly depend on the graph’s quality, which makes improving the graph quality

Learn how you can incorporate multimodal information into your machine-learning system Eivind Kjosbakken · Follow Published in Towards Data Science · 10 min read · 7 hours ago — In this article, I will discuss how you can incorporate information from different modalities into your machine learning system. These modalities can be information like an image, text, or audio. It can also, for example, be several images of the same object taken from different angles.

This article will show you how to make an RAG system that makes your data easily accessible via prompting. Eivind Kjosbakken · Follow Published in Towards Data Science · 13 min read · 5 hours ago — A RAG system is an innovative approach to information retrieval. It utilizes traditional information retrieval approaches like vector similarity search combined with state-of-the-art large language model technology. Combined, these technologies make up a robust system that can access