Skip to content

GitLab

Unverified Commit cc9f27bb authored by Susnato Dhar's avatar Susnato Dhar Committed by GitHub
Browse files

Remove padding_masks from `gpt_bigcode`. (#27348) 

Update modeling_gpt_bigcode.py
parent 8c91f15a
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 15 deletions
src/transformers/models/gpt_bigcode/modeling_gpt_bigcode.py
View file @ cc9f27bb
...@@ -235,16 +235,10 @@ class GPTBigCodeAttention(nn.Module): ...@@ -235,16 +235,10 @@ class GPTBigCodeAttention(nn.Module):
encoder_attention_mask: Optional[torch.Tensor] = None, encoder_attention_mask: Optional[torch.Tensor] = None,
use_cache: Optional[bool] = False, use_cache: Optional[bool] = False,
output_attentions: Optional[bool] = False, output_attentions: Optional[bool] = False,
**kwargs,
) -> Union[ ) -> Union[
Tuple[torch.Tensor, Optional[torch.Tensor]], Tuple[torch.Tensor, Optional[torch.Tensor]],
Tuple[torch.Tensor, Optional[torch.Tensor], Tuple[torch.Tensor, ...]], Tuple[torch.Tensor, Optional[torch.Tensor], Tuple[torch.Tensor, ...]],
]: ]:
if "padding_mask" in kwargs:
logger.warning_once(
"Passing `padding_mask` is deprecated and will be removed in v4.37. Please make sure use `attention_mask` instead.`"
)
if encoder_hidden_states is not None: if encoder_hidden_states is not None:
if not hasattr(self, "q_attn") or not self.is_cross_attention: if not hasattr(self, "q_attn") or not self.is_cross_attention:
raise ValueError( raise ValueError(
...@@ -308,19 +302,10 @@ class GPTBigCodeFlashAttention2(GPTBigCodeAttention): ...@@ -308,19 +302,10 @@ class GPTBigCodeFlashAttention2(GPTBigCodeAttention):
encoder_attention_mask: Optional[torch.Tensor] = None, encoder_attention_mask: Optional[torch.Tensor] = None,
use_cache: Optional[bool] = False, use_cache: Optional[bool] = False,
output_attentions: Optional[bool] = False, output_attentions: Optional[bool] = False,
**kwargs,
) -> Union[ ) -> Union[
Tuple[torch.Tensor, Optional[torch.Tensor]], Tuple[torch.Tensor, Optional[torch.Tensor]],
Tuple[torch.Tensor, Optional[torch.Tensor], Tuple[torch.Tensor, ...]], Tuple[torch.Tensor, Optional[torch.Tensor], Tuple[torch.Tensor, ...]],
]: ]:
if "padding_mask" in kwargs:
logger.warning_once(
"Passing `padding_mask` is deprecated and will be removed in v4.37. Please make sure use `attention_mask` instead.`"
)
# overwrite attention_mask with padding_mask
attention_mask = kwargs.pop("padding_mask")
if encoder_hidden_states is not None: if encoder_hidden_states is not None:
if not hasattr(self, "q_attn") or not self.is_cross_attention: if not hasattr(self, "q_attn") or not self.is_cross_attention:
raise ValueError( raise ValueError(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment