opendatalab/MinerU2.5-2509-1.2B

Note

This is a remotely-sourced model from the mineru_2_5 plugin, maintained by the community. It is not part of FiftyOne core and may have special installation requirements. Please review the plugin documentation and license before use.

MinerU2.5 is a 1.2B-parameter vision-language model for document parsing. It adopts a two-stage parsing strategy: first conducting efficient global layout analysis on downsampled images, then performing fine-grained content recognition on native-resolution crops for text, formulas, and tables..

Details

• Model name: opendatalab/MinerU2.5-2509-1.2B

• Model source: https://huggingface.co/opendatalab/MinerU2.5-2509-1.2B

• Model author: OpenDataLab

• Model license: AGPL-3.0

• Exposes embeddings? no

• Tags: detection, ocr, VLM

Requirements

• Packages: huggingface-hub, transformers, torch, torchvision, mineru-vl-utils

• CPU support

  • yes

• GPU support

  • yes

Example usage

import fiftyone as fo
import fiftyone.zoo as foz

foz.register_zoo_model_source("https://github.com/harpreetsahota204/mineru_2_5")

dataset = foz.load_zoo_dataset(
    "coco-2017",
    split="validation",
    dataset_name=fo.get_default_dataset_name(),
    max_samples=50,
    shuffle=True,
)

model = foz.load_zoo_model("opendatalab/MinerU2.5-2509-1.2B")

dataset.apply_model(model, label_field="predictions")

session = fo.launch_app(dataset)