# allenai/Molmo2-O-7B
#### NOTE
This is a [remotely-sourced model](../remote.md#model-zoo-remote) from the
[molmo2](../../plugins/plugins_ecosystem/molmo2.html) 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.
Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding..
**Details**
- Model name: `allenai/Molmo2-O-7B`
- Model source: [https://huggingface.co/allenai/Molmo2-O-7B](https://huggingface.co/allenai/Molmo2-O-7B)
- Model author: Allen Institute for AI (Ai2)
- Model license: Apache-2.0
- Exposes embeddings? no
- Tags: `torch, keypoints, zero-shot, video`
**Requirements**
- Packages: `huggingface-hub, transformers==4.57.1, torch, torchvision, molmo_utils, decord2, einops, accelerate`
- CPU support
- yes
- GPU support
- yes
**Example usage**
```python
import fiftyone as fo
import fiftyone.zoo as foz
foz.register_zoo_model_source("https://github.com/harpreetsahota204/molmo2")
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("allenai/Molmo2-O-7B")
dataset.apply_model(model, label_field="predictions")
session = fo.launch_app(dataset)
```