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

Cast predict scores to float before converting to numpy #2783

Merged
merged 2 commits into from
Jun 26, 2024
Merged

Cast predict scores to float before converting to numpy #2783

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
1184975
Cast predict scores to float before converting to numpy
malteos Jun 26, 2024
6ec6bf7
Add simple bfloat16 edge case test
tomaarsen Jun 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
2 changes: 1 addition & 1 deletion sentence_transformers/cross_encoder/CrossEncoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -441,7 +441,7 @@ def predict(
if convert_to_tensor:
pred_scores = torch.stack(pred_scores)
elif convert_to_numpy:
pred_scores = np.asarray([score.cpu().detach().numpy() for score in pred_scores])
pred_scores = np.asarray([score.cpu().detach().float().numpy() for score in pred_scores])

if input_was_string:
pred_scores = pred_scores[0]
Expand Down
10 changes: 10 additions & 0 deletions tests/test_cross_encoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
from pathlib import Path
from typing import Generator, List, Tuple

import numpy as np
import pytest
import torch
from torch.utils.data import DataLoader
Expand Down Expand Up @@ -171,3 +172,12 @@ def test_safe_serialization(safe_serialization: bool) -> None:
model.save(cache_folder, safe_serialization=safe_serialization)
model_files = list(Path(cache_folder).glob("**/pytorch_model.bin"))
assert 1 == len(model_files)


def test_bfloat16() -> None:
model = CrossEncoder("cross-encoder/stsb-distilroberta-base", automodel_args={"torch_dtype": torch.bfloat16})
score = model.predict([["Hello there!", "Hello, World!"]])
assert isinstance(score, np.ndarray)

ranking = model.rank("Hello there!", ["Hello, World!", "Heya!"])
assert isinstance(ranking, list)
Loading