Skip to content

Fix device placement for label_indices in LabelAttentionClassifier #62

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

Merged
meilame-tayebjee merged 2 commits into from
Jan 27, 2026
Merged

Fix device placement for label_indices in LabelAttentionClassifier #62

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bd3734f
Initial plan
Copilot Jan 26, 2026
af56bbe
fix: ensure label_indices uses correct device and dtype
Copilot Jan 26, 2026
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
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,3 +183,4 @@ example_files/
_site/
.quarto/
**/*.quarto_ipynb
my_ttc/
4 changes: 3 additions & 1 deletion torchTextClassifiers/model/components/text_embedder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -324,7 +324,9 @@ def forward(self, token_embeddings, compute_attention_matrix: Optional[bool] = F
compute_attention_matrix = bool(compute_attention_matrix)

# 1. Create label indices [0, 1, ..., C-1] for the whole batch
label_indices = torch.arange(self.num_classes).expand(B, -1)
label_indices = torch.arange(
self.num_classes, dtype=torch.long, device=token_embeddings.device
).expand(B, -1)

all_label_embeddings = self.label_embeds(
label_indices
Expand Down