Skip to content

fix: Fix colbert model shape mismatch #413

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
hh-space-invader merged 2 commits into from
Nov 28, 2024
Merged

fix: Fix colbert model shape mismatch #413

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0f0c4f4
fix: Fix colbert model shape mismatch
hh-space-invader Nov 25, 2024
affc7e9
refactor: Added the truncation after tokenizer init
hh-space-invader Nov 26, 2024
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
3 changes: 3 additions & 0 deletions fastembed/late_interaction/colbert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,6 +191,9 @@ def load_onnx_model(self) -> None:
self.tokenizer.encode(symbol, add_special_tokens=False).ids[0]
for symbol in string.punctuation
}
current_max_length = self.tokenizer.truncation["max_length"]
# ensure not to overflow after adding document-marker
self.tokenizer.enable_truncation(max_length=current_max_length - 1)

def embed(
self,
Expand Down