Instructions to use microsoft/OmniParser-v2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/OmniParser-v2.0 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("microsoft/OmniParser-v2.0", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Error in execution After deploying this model using Inference Endpoints
#27
by aniel1 - opened
I have deployed this on CPU, AWS server and testing the endpoint.
Input payload :
{
"inputs":
{"image": "data:image/png;base64,AddBase64Data",
"image_size": {"w": 640, "h": 640},
"bbox_threshold": 0.05,
"iou_threshold": 0.1
}
}
Output :
Error showing this message :
Input type (float) and bias type (c10::Half) should be the same
Please let me know where is the issue and how to fix this?