/databricks/python/lib/python3.8/site-packages/transformers/models/lilt/modeling_lilt.py in forward(self, input_ids, bbox, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, labels, output_attentions, output_hidden_states, return_dict)
   1028         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
   1029 
-> 1030         outputs = self.lilt(
   1031             input_ids,
   1032             bbox=bbox,

/databricks/python/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
   1188         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1189                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1190             return forward_call(*input, **kwargs)
   1191         # Do not call functions when jit is used
   1192         full_backward_hooks, non_full_backward_hooks = [], []

/databricks/python/lib/python3.8/site-packages/transformers/models/lilt/modeling_lilt.py in forward(self, input_ids, bbox, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, output_attentions, output_hidden_states, return_dict)
    816         )
    817 
--> 818         layout_embedding_output = self.layout_embeddings(bbox=bbox, position_ids=position_ids)
    819 
    820         encoder_outputs = self.encoder(

/databricks/python/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
   1188         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1189                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1190             return forward_call(*input, **kwargs)
   1191         # Do not call functions when jit is used
   1192         full_backward_hooks, non_full_backward_hooks = [], []

/databricks/python/lib/python3.8/site-packages/transformers/models/lilt/modeling_lilt.py in forward(self, bbox, position_ids)
    179             dim=-1,
    180         )
--> 181         spatial_position_embeddings = self.box_linear_embeddings(spatial_position_embeddings)
    182         box_position_embeddings = self.box_position_embeddings(position_ids)
    183 

/databricks/python/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
   1188         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1189                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1190             return forward_call(*input, **kwargs)
   1191         # Do not call functions when jit is used
   1192         full_backward_hooks, non_full_backward_hooks = [], []

/databricks/python/lib/python3.8/site-packages/torch/nn/modules/linear.py in forward(self, input)
    112 
    113     def forward(self, input: Tensor) -> Tensor:
--> 114         return F.linear(input, self.weight, self.bias)
    115 
    116     def extra_repr(self) -> str:

RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`