<!-- # hard line break macro for HTML -->

<a id="model-zoo-glm-ocr-torch"></a>

# glm-ocr-torch

GLM-OCR, a 0.9B vision-language model that transcribes document images to text.

**Details**

- Model name: `glm-ocr-torch`
- Model source: [https://huggingface.co/zai-org/GLM-OCR](https://huggingface.co/zai-org/GLM-OCR)
- Model author: Z.ai
- Model license: MIT
- Model size: 2.47 GB
- Exposes embeddings? no
- Tags: `ocr, classification, torch`

**Requirements**

- Packages: `torch, transformers>=5.14`
- CPU support
  - yes
- GPU support
  - yes

**Example usage**

```python
import fiftyone as fo
import fiftyone.zoo as foz

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("glm-ocr-torch")

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

session = fo.launch_app(dataset)
```