H2OVL-Mississippi Vision Language Models Technical Report

TL;DR

This paper introduces two small vision-language models, H2OVL-Mississippi-0.8B and 2B, trained on 37 million image-text pairs, achieving state-of-the-art text recognition and competitive performance on benchmarks, enabling privacy-focused on-device applications.

Contribution

Development of small, efficient vision-language models trained on large datasets, extending prior language models into visual understanding, and releasing them openly for broad accessibility.

Findings

H2OVL-Mississippi-0.8B achieves state-of-the-art OCR performance.

H2OVL-Mississippi-2B shows competitive results across benchmarks.

Models are suitable for privacy-sensitive, on-device applications.

Abstract

Smaller vision-language models (VLMs) are becoming increasingly important for privacy-focused, on-device applications due to their ability to run efficiently on consumer hardware for processing enterprise commercial documents and images. These models require strong language understanding and visual capabilities to enhance human-machine interaction. To address this need, we present H2OVL-Mississippi, a pair of small VLMs trained on 37 million image-text pairs using 240 hours of compute on 8 x H100 GPUs. H2OVL-Mississippi-0.8B is a tiny model with 0.8 billion parameters that specializes in text recognition, achieving state of the art performance on the Text Recognition portion of OCRBench and surpassing much larger models in this area. Additionally, we are releasing H2OVL-Mississippi-2B, a 2 billion parameter model for general use cases, exhibiting highly competitive metrics across various academic benchmarks. Both models build upon our prior work with H2O-Danube language models, extending their capabilities into the visual domain. We release them under the Apache 2.0 license, making VLMs accessible to everyone, democratizing document AI and visual LLMs.