Skip to content

Add truncation to CLIP model #2969

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
tomaarsen merged 6 commits into from
Mar 24, 2025
+26 −1
Merged

Add truncation to CLIP model #2969

Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
9aeaf14
Add truncation to CLIP model
MrLoh Oct 1, 2024
cdeff8c
Avoid allowing users to specify max_seq_length currently
tomaarsen Mar 21, 2025
c694225
add max_seq_length getter and setter to clip
MrLoh Mar 21, 2025
a6ef50f
Add test to verify CLIP max length getter/setter
tomaarsen Mar 24, 2025
fa07b45
Merge branch 'master' into pr-2969
tomaarsen Mar 24, 2025
9622821
Run formatter
tomaarsen Mar 24, 2025
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 sentence_transformers/models/CLIPModel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ def tokenize(self, texts, padding: str | bool = True) -> dict[str, torch.Tensor]

encoding = {}
if len(texts_values):
encoding = self.processor.tokenizer(texts_values, return_tensors="pt", padding=padding)
encoding = self.processor.tokenizer(texts_values, padding=padding, truncation=True, return_tensors="pt")

if len(images):
image_features = self.processor.image_processor(images, return_tensors="pt")
Expand Down
Loading