RuntimeError: expand(torch.FloatTensor{[1, 8, 263, 4]}, size=[8, 263, 4]): the number of sizes provided (3) must be greater or equal to the number of dimensions in the tensor (4)

nlp
1 
 max_len = max(len(bbox) for bbox in bbox_list)
    padded_bbox_list = [bbox + [[0, 0, 0, 0]] * (max_len - len(bbox)) for bbox in bbox_list]
    bbox_tensor = torch.tensor(padded_bbox_list, dtype=torch.float32)

    
    bbox_tensor = bbox_tensor.unsqueeze(0)
    bbox_tensor = bbox_tensor.expand(encoded_inputs['input_ids'].shape[0], max_len, 4)

runtimeerror: expand(torch.floatTensor{[1,8,263,4]}, size=[8,263,4]):