allenai/MolmoPoint-Img-8B#

From Plugin

Note

This is a remotely-sourced model from the molmo_point 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.

MolmoPoint-Img-8B is a vision-language model specialised for pointing at UI elements and objects in screenshots. Given a text prompt, it returns normalized keypoint coordinates for each matching element found..

Details

  • Model name: allenai/MolmoPoint-Img-8B

  • Model source: https://huggingface.co/allenai/MolmoPoint-Img-8B

  • Model author: Allen AI

  • Model license: Apache-2.0

  • Exposes embeddings? no

  • Tags: keypoints, pointing, VLM, zero-shot, image-text-to-text, UI, screenshots

Requirements

  • Packages: torch, transformers, pillow, huggingface-hub, molmo-utils

  • CPU support

    • yes

  • GPU support

    • yes

Example usage

 1import fiftyone as fo
 2import fiftyone.zoo as foz
 3
 4foz.register_zoo_model_source("https://github.com/harpreetsahota204/molmo_point")
 5
 6dataset = foz.load_zoo_dataset(
 7    "coco-2017",
 8    split="validation",
 9    dataset_name=fo.get_default_dataset_name(),
10    max_samples=50,
11    shuffle=True,
12)
13
14model = foz.load_zoo_model("allenai/MolmoPoint-Img-8B")
15
16dataset.apply_model(model, label_field="predictions")
17
18session = fo.launch_app(dataset)