# vidore/colqwen2.5-v0.2
#### NOTE
This is a [remotely-sourced model](../remote.md#model-zoo-remote) from the
[colqwen2_5_v0_2](../../plugins/plugins_ecosystem/colqwen2_5_v0_2.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.
ColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a Qwen2.5-VL-3B extension that generates ColBERT- style multi-vector representations of text and images..
**Details**
- Model name: `vidore/colqwen2.5-v0.2`
- Model source: [https://huggingface.co/vidore/colqwen2.5-v0.2](https://huggingface.co/vidore/colqwen2.5-v0.2)
- Model author: Vidore
- Model license: Apache 2.0
- Exposes embeddings? yes
- Tags: `classification, logits, embeddings, torch, visual-document-retrieval, zero-shot`
**Requirements**
- Packages: `huggingface-hub, transformers, torch, torchvision, colpali-engine`
- 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/colqwen2_5_v0_2")
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("vidore/colqwen2.5-v0.2")
dataset.apply_model(model, label_field="predictions")
session = fo.launch_app(dataset)
```