Raspberry PI 5 docker image does not support my model (yolo_nas_m) for object detection

Hello,

I have trained YOLO-NAS model on my dataset and want to run inference on a Raspberry Pi5 device. I am using this tutorial to do that ( Raspberry Pi | Roboflow Docs

My project type is object detection and the model is YOLO-NAS Object Detection (Medium)

However, when I run inference I get 500 status error on the inference server

The error on the server:
Traceback (most recent call last):
File “/app/inference/core/interfaces/http/http_api.py”, line 68, in wrapped_route
return await route(*args, **kwargs)
File “/app/inference/core/interfaces/http/http_api.py”, line 803, in legacy_infer
model = self.model_registry.get_model(model_id, api_key)(
File “/app/inference/core/registries/decorators/fixed_device_id.py”, line 38, in get_model
model_class = self.registry.get_model(model_id, api_key)
File “/app/inference/core/registries/roboflow.py”, line 38, in get_model
raise DatasetLoadError(f"Model type not supported: {model_type}")
inference.core.exceptions.DatasetLoadError: Model type not supported: (‘object-detection’, ‘yolo_nas_m’)

On Raspberry pi 5 I am using the docker container roboflow/roboflow-inference-server-arm-cpu.
What models are supported for this type of container?