GPTNeoX needs kwargs

Author: ArthurZucker

src/transformers/models/gpt_neox/modeling_gpt_neox.py

@@ -1081,6 +1081,7 @@ def forward(
         output_hidden_states: Optional[bool] = None,
         return_dict: Optional[bool] = None,
         cache_position: Optional[torch.LongTensor] = None,
+        **kwargs, # Unused for now, mostly for the loss correction
     ) -> Union[Tuple, CausalLMOutputWithPast]:
         r"""
         labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):