NVIDIA Nemotron Parse v1.2 is an image-text-to-text model designed for document understanding and parsing tasks. It accepts both visual and textual inputs and produces structured outputs. The model is available on Hugging Face with Transformers support and is part of NVIDIA's Nemotron family of models.
In the Computer vision, OCR & document AI space, NVIDIA Nemotron Parse takes a focused approach. It focuses on extracting structured information from mixed image and text documents at scale. It is built as an open-source project for AI developers and enterprise users. NVIDIA Nemotron Parse is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
NVIDIA builds and maintains NVIDIA Nemotron Parse, and it first shipped in 2023. The project is developed in the open on GitHub with 86.8k stars and 3k commits in the last 90 days.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do