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

Jump to bottom

FIX: Small regression in BNB LoRA output #2238

Merged
merged 1 commit into from
Nov 28, 2024
Merged

FIX: Small regression in BNB LoRA output #2238

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 8 additions & 6 deletions src/peft/tuners/lora/bnb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -235,15 +235,15 @@ def forward(self, x: torch.Tensor, *args, **kwargs) -> torch.Tensor:
x = x.to(compute_dtype)

if not self.use_dora[active_adapter]:
result = result + lora_B(lora_A(dropout(x))) * scaling
output = lora_B(lora_A(dropout(x))) * scaling
else:
if isinstance(dropout, torch.nn.Identity) or not self.training:
base_result = result
else:
x = dropout(x)
base_result = None

result = result + self.lora_magnitude_vector[active_adapter](
output = self.lora_magnitude_vector[active_adapter](
x,
lora_A=lora_A,
lora_B=lora_B,
Expand All @@ -252,7 +252,8 @@ def forward(self, x: torch.Tensor, *args, **kwargs) -> torch.Tensor:
base_result=base_result,
)
if requires_conversion:
result = result.to(expected_dtype)
output = output.to(expected_dtype)
result = result + output

return result

Expand Down Expand Up @@ -490,15 +491,15 @@ def forward(self, x: torch.Tensor, *args, **kwargs) -> torch.Tensor:
x = x.to(lora_A.weight.dtype)

if not self.use_dora[active_adapter]:
result = result + lora_B(lora_A(dropout(x))) * scaling
output = lora_B(lora_A(dropout(x))) * scaling
else:
if isinstance(dropout, torch.nn.Identity) or not self.training:
base_result = result
else:
x = dropout(x)
base_result = None

result = result + self.lora_magnitude_vector[active_adapter](
output = self.lora_magnitude_vector[active_adapter](
x,
lora_A=lora_A,
lora_B=lora_B,
Expand All @@ -507,7 +508,8 @@ def forward(self, x: torch.Tensor, *args, **kwargs) -> torch.Tensor:
base_result=base_result,
)
if requires_conversion:
result = result.to(expected_dtype)
output = output.to(expected_dtype)
result = result + output

return result

Expand Down
Loading