Skip to content

bug fix: duplicate padding for offline mode #448

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
jiapingW merged 2 commits into from
Jan 22, 2026
Merged

bug fix: duplicate padding for offline mode #448

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2092418
fix duplicate padding for offline mode
uygnef Jan 22, 2026
07d8dc0
clean up
uygnef Jan 22, 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
5 changes: 2 additions & 3 deletions specforge/data/preprocessing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,6 @@
HAS_QWEN_VL_UTILS = False
process_vision_info = None

from specforge.utils import padding

from .parse import GeneralParser, HarmonyParser, ThinkingParser
from .template import TEMPLATE_REGISTRY, ChatTemplate
Expand Down Expand Up @@ -464,9 +463,9 @@ def process_data(data, max_len, transform=None):

new_data["attention_mask"] = torch.ones_like(loss_mask, dtype=torch.long)
new_data["loss_mask"] = loss_mask
new_data["target"] = padding(target, left=False)
new_data["target"] = target
new_data["hidden_state"] = hidden_state
new_data["input_ids"] = padding(input_ids, left=False)
new_data["input_ids"] = input_ids
if transform:
new_data = transform(new_data)
return new_data
Expand Down