Skip to content

Initialization for LoRA weights A and B initialized in the wrong way. #155

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

Open
arun477 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Initialization for LoRA weights A and B initialized in the wrong way. #155

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a951910
Fix initialization of lora_A and lora_B
arun477 Jan 27, 2024
2ad4d86
Merge pull request #1 from arun477/arun477-lora-initialization-patch-1
arun477 Jan 27, 2024
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
4 changes: 2 additions & 2 deletions loralib/layers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,8 +56,8 @@ def reset_parameters(self):
nn.Embedding.reset_parameters(self)
if hasattr(self, 'lora_A'):
# initialize A the same way as the default for nn.Linear and B to zero
nn.init.zeros_(self.lora_A)
nn.init.normal_(self.lora_B)
nn.init.normal_(self.lora_A)
nn.init.zeros_(self.lora_B)

def train(self, mode: bool = True):
nn.Embedding.train(self, mode)
Expand Down