# zai-org/GLM-OCR
#### NOTE
This is a [remotely-sourced model](../remote.md#model-zoo-remote) from the
[glm_ocr](../../plugins/plugins_ecosystem/glm_ocr.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.
GLM-OCR is a vision-language model for document understanding. Supports text recognition, formula recognition, table recognition, and custom structured extraction via JSON prompts..
**Details**
- Model name: `zai-org/GLM-OCR`
- Model source: [https://huggingface.co/zai-org/GLM-OCR](https://huggingface.co/zai-org/GLM-OCR)
- Model author: zai-org
- Model license: Apache-2.0
- Exposes embeddings? no
- Tags: `ocr, document-understanding, visual-document-retrieval`
**Requirements**
- Packages: `torch, transformers`
- 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/glm_ocr")
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("zai-org/GLM-OCR")
dataset.apply_model(model, label_field="predictions")
session = fo.launch_app(dataset)
```