'RyzenAIModelForImageClassification' object has no attribute 'device'

[dancrab17]

I followed the instructions and run the code below provided by the example:
import requests
from PIL import Image

• from transformers import AutoModelForImageClassification

• from optimum.amd.ryzenai import RyzenAIModelForImageClassification
  from transformers import AutoFeatureExtractor, pipeline

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

model_id =

• model = AutoModelForImageClassification.from_pretrained(model_id)

• model = RyzenAIModelForImageClassification.from_pretrained(model_id)
  feature_extractor = AutoFeatureExtractor.from_pretrained(model_id)
  cls_pipe = pipeline("image-classification", model=model, feature_extractor=feature_extractor)
  outputs = cls_pipe(image)

but I got error below:
AttributeError Traceback (most recent call last)
Cell In[3], line 3
1 model = RyzenAIModelForImageClassification.from_pretrained(model_id)
2 feature_extractor = AutoFeatureExtractor.from_pretrained(model_id)
----> 3 cls_pipe = pipeline("image-classification", model=model, feature_extractor=feature_extractor, token=token1)
4 outputs = cls_pipe(image)

File ~\anaconda3\envs\ryzenai-1.1-20240608-152949\lib\site-packages\transformers\pipelines_init_.py:1108, in pipeline(task, model, config, tokenizer, feature_extractor, image_processor, framework, revision, use_fast, token, device, device_map, torch_dtype, trust_remote_code, model_kwargs, pipeline_class, **kwargs)
1105 if device is not None:
1106 kwargs["device"] = device
-> 1108 return pipeline_class(model=model, framework=framework, task=task, **kwargs)

File ~\anaconda3\envs\ryzenai-1.1-20240608-152949\lib\site-packages\transformers\pipelines\image_classification.py:89, in ImageClassificationPipeline.init(self, *args, **kwargs)
88 def init(self, *args, **kwargs):
---> 89 super().init(*args, **kwargs)
90 requires_backends(self, "vision")
91 self.check_model_type(
92 TF_MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES
93 if self.framework == "tf"
94 else MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES
95 )

File ~\anaconda3\envs\ryzenai-1.1-20240608-152949\lib\site-packages\transformers\pipelines\base.py:848, in Pipeline.init(self, model, tokenizer, feature_extractor, image_processor, modelcard, framework, task, args_parser, device, torch_dtype, binary_output, **kwargs)
845 device = -1
847 if is_torch_available() and self.framework == "pt":
--> 848 if device == -1 and self.model.device is not None:
849 device = self.model.device
850 if isinstance(device, torch.device):

AttributeError: 'RyzenAIModelForImageClassification' object has no attribute 'device'

[joshuachris2001]

Same error.
I am using the example codes from [https://huggingface.co/docs/optimum/main/en/amd/ryzenai/overview] yet I'm still getting errors.