Update modeling_iquestcoder.py

modeling_iquestcoder.py

@@ -48,7 +48,6 @@ from transformers.modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_u
 from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
 from transformers.processing_utils import Unpack
 from transformers.utils import (
-    LossKwargs,
     auto_docstring,
     can_return_tuple,
     is_torch_flex_attn_available,
@@ -705,10 +704,6 @@ class IQuestCoderModel(IQuestCoderPreTrainedModel):
 # Model Heads
 # =============================================================================
 
-class KwargsForCausalLM(FlashAttentionKwargs, LossKwargs):
-    ...
-
-
 @auto_docstring
 class IQuestCoderForCausalLM(IQuestCoderPreTrainedModel, GenerationMixin):
     """IQuestCoder Model with a language modeling head on top for causal LM."""
@@ -759,7 +754,7 @@ class IQuestCoderForCausalLM(IQuestCoderPreTrainedModel, GenerationMixin):
         output_hidden_states: Optional[bool] = None,
         cache_position: Optional[torch.LongTensor] = None,
         logits_to_keep: Union[int, torch.Tensor] = 0,
-        **kwargs: Unpack[KwargsForCausalLM],
+        **kwargs
     ) -> CausalLMOutputWithPast:
         r"""
         Args: