Florence Model stuck in forever loop

[ribhav99]

line 110 of utils.py: generated_ids = model.generate(input_ids=inputs["input_ids"],pixel_values=inputs["pixel_values"],max_new_tokens=100,num_beams=3, do_sample=False)

This line runs forever on macbook pro m2 pro. paddleocr==2.9.1 paddlepaddle==3.0.0b1 numpy==1.26.4

I traced it into the library code. Florence2ForConditionalGeneration class _encode_image method is where it gets stuck. Specifically on this line within the method: x = self.vision_tower.forward_features_unpool(pixel_values)

Can anyone help me out with this?