| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| mteb-2.18.14.tar.gz | 2026-08-05 | 4.0 MB | |
| mteb-2.18.14.tar.gz.publish.attestation | 2026-08-05 | 9.8 kB | |
| mteb-2.18.14-py3-none-any.whl | 2026-08-05 | 6.1 MB | |
| mteb-2.18.14-py3-none-any.whl.publish.attestation | 2026-08-05 | 9.8 kB | |
| 2.18.14 source code.tar.gz | 2026-08-05 | 12.0 MB | |
| 2.18.14 source code.zip | 2026-08-05 | 14.4 MB | |
| README.md | 2026-08-05 | 793 Bytes | |
| Totals: 7 Items | 36.5 MB | 1 | |
2.18.14 (2026-08-05)
Fix
- fix: mock zeroshot tasks must declare the text modality (#5093)
Zeroshot classification scores inputs against candidate text prompts, so these tasks require a text tower. The audio, video and video+audio mocks omitted "text" from metadata.modalities, so get_compatible_mock_tasks selected them for audio-only and video-only models, which then fail with KeyError on the input column. The image mock and every real zeroshot task already declare text.
Co-authored-by: Hubert Lu <hubielu@email.com> (f7c910d)
Unknown
- fix tests (#5089) (
c1c888e)