remove unnecessary kwargs from JambaAttentionDecoderLayer and JambaMa…

…mbaDecoderLayer
AI21Labs · Mar 31, 2024 · ce8b476 · ce8b476
1 parent 59d832a
commit ce8b476
Showing 1 changed file with 0 additions and 2 deletions.
diff --git a/src/transformers/models/jamba/modeling_jamba.py b/src/transformers/models/jamba/modeling_jamba.py
@@ -1242,7 +1242,6 @@ def forward(
         output_attentions: Optional[bool] = False,
         output_router_logits: Optional[bool] = False,
         use_cache: Optional[bool] = False,
-        **kwargs,
     ) -> Tuple[torch.FloatTensor, Optional[Tuple[torch.FloatTensor, torch.FloatTensor]]]:
         if "padding_mask" in kwargs:
             warnings.warn(
@@ -1321,7 +1320,6 @@ def forward(
         output_attentions: Optional[bool] = False,
         output_router_logits: Optional[bool] = False,
         use_cache: Optional[bool] = False,
-        **kwargs,
     ) -> Tuple[torch.FloatTensor, Optional[Tuple[torch.FloatTensor, torch.FloatTensor]]]:
         if "padding_mask" in kwargs:
             warnings.warn(