Blog

How Agents Integrate into the Paradigm Platform to Automate Complex Tasks

With the rise of generative AI, the possibilities for automating complex and repetitive tasks have never been greater. At LightOn, our teams are working on integrating agent-based behaviors to meet this objective. In this article, we’ll present our advancements in this area.

FC-AMF-OCR Dataset : LightOn releases a 9.3 million images OCR dataset to improve real world document parsing

With over 9.3 million annotated images, this dataset offers researchers and AI developers a valuable resource for creating models adapted to real world documents.

Chat with Document: How This Technology is Revolutionizing Business Productivity

The 'chat with document' revolutionizes business productivity by providing instant answers based on internal documents. Learn how Paradigm can help you implement it effectively.

RAG (Retrieval-Augmented Generation): Transforming Information Retrieval and AI Interaction

RAG (Retrieval-Augmented Generation) transforms AI interaction by combining retrieval and generation for more accurate, context-aware responses. Learn how RAG can benefit your business.

LightOn Pulse #2: Discover the New Paradigm Platform Updates

Version Glorious-Giraffe 20240828 Release Date: August 28, 2024

PyLate: Flexible Training and Retrieval for ColBERT Models

We release PyLate, a new user-friendly library for training and experimenting with ColBERT models, a family of models that exhibit strong retrieval capabilities on out-of-domain data.

ArabicWeb24: Creating a high quality Arabic Web-only pre-training dataset

LightOn Pulse #1

Innovations and Advancements (2024.07)

Training Mamba Models on AMD MI250/MI250X GPUs with Custom Kernels

In this blogpost we show how we can train a Mamba model interchangeably on both NVIDIA and AMD and we compare both training performance and convergence in both cases. This shows that our training stack is becoming more GPU-agnostic.