H2OVL-Mississippi Vision Language Models Technical Report
This work addresses privacy-focused, on-device processing of enterprise documents and images, making VLMs more accessible, though it is incremental as it builds upon prior language models.
The authors tackled the need for efficient vision-language models for on-device applications by presenting H2OVL-Mississippi, a pair of small models trained on 37 million image-text pairs, with the 0.8B version achieving state-of-the-art performance on text recognition benchmarks and the 2B version showing competitive results across various tasks.
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.