Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix arg in bettertransformer llama attention #1421

Merged
merged 3 commits into from
Oct 3, 2023
+7 −0
Merged

Fix arg in bettertransformer llama attention #1421

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
498c4b8
fix arg in llama attention
SunMarc Sep 28, 2023
d0f27d2
change to kwargs
SunMarc Sep 29, 2023
b67fb2a
add kwargs everwhere
younesbelkada Oct 3, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions optimum/bettertransformer/models/attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,6 +242,7 @@ def opt_forward(
attention_mask: Optional[torch.Tensor] = None,
layer_head_mask: Optional[torch.Tensor] = None,
output_attentions: bool = False,
**kwargs,
) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
raise_on_head_mask(layer_head_mask)

Expand Down Expand Up @@ -336,6 +337,7 @@ def t5_forward(
query_length=None,
use_cache=False,
output_attentions=False,
**kwargs,
):
raise_on_head_mask(layer_head_mask)

Expand Down Expand Up @@ -466,6 +468,7 @@ def bart_forward(
attention_mask: Optional[torch.Tensor] = None,
layer_head_mask: Optional[torch.Tensor] = None,
output_attentions: bool = False,
**kwargs,
) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
"""Input shape: Batch x Time x Channel"""
raise_on_head_mask(layer_head_mask)
Expand Down Expand Up @@ -583,6 +586,7 @@ def llama_forward(
past_key_value: Optional[Tuple[torch.Tensor]] = None,
output_attentions: bool = False,
use_cache: bool = False,
**kwargs,
) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
if output_attentions is True:
raise ValueError("output_attentions=True can not be supported with BetterTransformer.")
Expand Down Expand Up @@ -768,6 +772,7 @@ def gpt_bigcode_forward(
encoder_attention_mask: Optional[torch.Tensor] = None,
use_cache: Optional[bool] = False,
output_attentions: Optional[bool] = False,
**kwargs,
) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
if output_attentions is True:
raise ValueError("output_attentions=True can not be supported with BetterTransformer.")
Expand Down Expand Up @@ -826,6 +831,7 @@ def bloom_forward(
head_mask: Optional[torch.Tensor] = None,
use_cache: bool = False,
output_attentions: bool = False,
**kwargs,
):
raise_on_head_mask(head_mask)

Expand Down Expand Up @@ -910,6 +916,7 @@ def falcon_forward(
head_mask: Optional[torch.Tensor] = None,
use_cache: bool = False,
output_attentions: bool = False,
**kwargs,
):
fused_qkv = self.query_key_value(hidden_states) # [batch_size, seq_length, 3 x hidden_size]
num_kv_heads = self.num_heads if self.new_decoder_architecture else self.num_kv_heads
Expand Down
Loading