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

deduplication in GISTEmbedLoss and CachedGISTEmbedLoss #3074

Draft
wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

deduplication in GISTEmbedLoss and CachedGISTEmbedLoss #3074

Show file tree
Hide file tree
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
4 changes: 2 additions & 2 deletions sentence_transformers/losses/CachedGISTEmbedLoss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -265,7 +265,7 @@ def calculate_loss_and_cache_gradients(self, reps: list[list[Tensor]], reps_guid
# Apply thresholds based on guided model similarities
ap_sim[guided_ap_sim > guided_sim] = -torch.inf
aa_sim[guided_aa_sim > guided_sim] = -torch.inf
pp_sim[guided_pp_sim > guided_sim] = -torch.inf
pp_sim[guided_pp_sim >= guided_sim] = -torch.inf

# Concatenate the similarity matrices for anchor-positive, anchor-anchor, and positive-positive
scores = torch.cat([ap_sim, aa_sim, pp_sim], dim=1)
Expand Down Expand Up @@ -328,7 +328,7 @@ def calculate_loss(self, reps: list[list[Tensor]], reps_guided: list[list[Tensor
# Apply thresholds based on guided model similarities
ap_sim[guided_ap_sim > guided_sim] = -torch.inf
aa_sim[guided_aa_sim > guided_sim] = -torch.inf
pp_sim[guided_pp_sim > guided_sim] = -torch.inf
pp_sim[guided_pp_sim >= guided_sim] = -torch.inf

# Concatenate the similarity matrices for anchor-positive, anchor-anchor, and positive-positive
scores = torch.cat([ap_sim, aa_sim, pp_sim], dim=1)
Expand Down
2 changes: 1 addition & 1 deletion sentence_transformers/losses/GISTEmbedLoss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,7 +150,7 @@ def forward(self, sentence_features: Iterable[dict[str, Tensor]], labels: Tensor
# the loss.
ap_sim[guided_ap_sim > guided_sim] = -torch.inf
aa_sim[guided_aa_sim > guided_sim] = -torch.inf
pp_sim[guided_pp_sim > guided_sim] = -torch.inf
pp_sim[guided_pp_sim >= guided_sim] = -torch.inf

scores = [ap_sim, aa_sim, pp_sim]

Expand Down