Skip to content

Bug fixing #441

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
oleksost merged 2 commits into from
Jan 8, 2026
Merged

Bug fixing #441

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
9b4e287
test lm head
oleksost Jan 7, 2026
7a2142d
test ssm
oleksost Jan 7, 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
2 changes: 1 addition & 1 deletion tests/layers/test_lm_head.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ def _reverse_kl_loss(
loss_per_sample = torch.nn.functional.kl_div(
teacher_log_probs, student_log_probs, reduction="none", log_target=True
).sum(dim=-1)
loss = (loss_per_sample * loss_mask.flatten()).sum() / loss_mask.sum()
loss = (loss_per_sample * loss_mask.flatten()).mean()
return loss


Expand Down
5 changes: 0 additions & 5 deletions tests/layers/test_ssm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,11 +19,6 @@
Apriel2GatedDeltaNet = None
Apriel2Mamba = None

try:
from fast_llm_external_models.apriel_hybrid_ssm.modeling_apriel_hybrid_ssm import KimiDeltaAttention
except ImportError:
KimiDeltaAttention = None

HIDDEN_SIZE = 16
SEQ_LEN = 65

Expand Down