Update modeling_deepseek.py

modeling_deepseek.py

@@ -22,7 +22,6 @@ 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,
     add_start_docstrings,
     add_start_docstrings_to_model_forward,
     can_return_tuple,
@@ -903,9 +902,6 @@ class DeepseekV3Model(DeepseekV3PreTrainedModel):
         return causal_mask
 
 
-class KwargsForCausalLM(FlashAttentionKwargs, LossKwargs): ...
-
-
 class DeepseekV3ForCausalLM(DeepseekV3PreTrainedModel, GenerationMixin):
     _tied_weights_keys = ["lm_head.weight"]
     _tp_plan = {"lm_head": "colwise_rep"}
@@ -955,7 +951,7 @@ class DeepseekV3ForCausalLM(DeepseekV3PreTrainedModel, 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"""
             labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):