OS-Copilot/OS-Atlas-Base-7B

Note

This is a remotely-sourced model from the os_atlas 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.

OS-Atlas provides a series of models specifically designed for GUI agents..

Details

• Model name: OS-Copilot/OS-Atlas-Base-7B

• Model source: https://huggingface.co/OS-Copilot/OS-Atlas-Base-7B

• Model author: OS-Copilot

• Model license: Apache 2.0

• Exposes embeddings? no

• Tags: detection, ocr, VLM, classification, zero-shot, visual-agent

Requirements

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

• 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/os_atlas")

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("OS-Copilot/OS-Atlas-Base-7B")

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

session = fo.launch_app(dataset)