LightOnOCR-2-1B is a multimodal model developed by LightOn for high-performance optical character recognition and document understanding tasks. It supports vision-language inputs and uses a custom chat template for processing image and text data together.
In the Foundation models & chat space, LightOnOCR 2 1B takes a focused approach. It focuses on extracting text from images and documents using AI. It is built as an open-source project for developers. LightOnOCR 2 1B is open source under the Open Source license. The product ships for the web, the command line, and API.
LightOn builds and maintains LightOnOCR 2 1B, and the product first shipped in 2026. Key capabilities include OCR, multimodal, and Vision Language.
Latest indexed changes and source events
lightonai/LightOnOCR-2-1B verified by the PulseGate indexer
Other apps tracked under the same category.
