Releases: embeddings-benchmark/mteb
1.6.1
1.6.0
1.6.0 (2024-04-10)
Documentation
Feature
-
feat: Added new language code standard (#326)
-
fix: Added initial language code suggestion
-
docs: updated task metadata description
-
fix: changed folder structure to iso 639-3 codes
-
fix: Updated all language tags
-
clean: removed accidental results commit
-
fix: Add trusting of remote code to remove warning
-
fix: Added formatting
-
fix: trust remote code the flores dataset
-
docs: Added point for language rewrite
-
fix: reran linter after merge
-
fix: Added corrections from review
-
fix: Updated languages for newly added datasets
-
docs: added points for new annotations (
f0daece
)
1.5.6
1.5.6 (2024-04-10)
Documentation
- docs: add points and affiliation for MartinBernstorff (#335)
docs: update points.md (2903cb4
)
Fix
-
fix: Added medical qa dataset (#333)
-
Added news classification dataset.
-
Fixes on suggestions
-
Added new medical qa dataset
-
Update model run files and model path
-
Added points for dataset.
-
Fixes
Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com> (80acc3e
)
Unknown
- Update pull_request_template.md (
84cffa2
)
1.5.5
1.5.4
1.5.4 (2024-04-08)
Fix
-
fix: Multiple dataset fixes (#328)
-
fix: remove time of run (as it does not relate to the model itself). Time of run should be on the dataset results
-
fix: fixes the PawsX datasets
-
docs: Updated points
-
fix: flores clustering
-
fix: mulitple dataset fixes
-
docs: updated points
-
fix: added missing dataset_transform to multitask task
-
syle: ran formatter
-
fix: correctly fix pawsX (
84408f7
)
1.5.3
1.5.3 (2024-04-08)
Documentation
-
docs: Added point for SEB (#318)
-
docs: added points for seb
-
docs: added points for seb (
ca64fc7
) -
docs: Small fixes in readme.md (#317)
Fix typos in readme.md (ede12c8
)
Fix
-
fix: Added English news classification dataset (#323)
-
Fix typos in readme.md
-
Added news classification dataset.
-
Added news classification dataset.
-
Fixes on suggestions
-
Update docs/mmteb/points.md
Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com>
Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com> (4d21807
)
Unknown
-
Fix name (
d69bf94
) -
Add law datasets (#311)
-
add command
-
add datasets
-
reformat dataset
-
Rephrase description
-
Update mteb/tasks/Retrieval/law/GerDaLIRRetrieval.py
-
Update mteb/tasks/Retrieval/law/GerDaLIRRetrieval.py
-
Update mteb/init.py
-
Update scripts/run_mteb_law.py
-
Update scripts/run_mteb_law.py
-
Update mteb/init.py
-
Update mteb/tasks/Retrieval/init.py
-
Update mteb/tasks/Retrieval/law/GerDaLIRRetrieval.py
-
Update mteb/tasks/Retrieval/law/GerDaLIRRetrieval.py
-
Update mteb/tasks/Retrieval/law/LegalQuADRetrieval.py
-
Update mteb/tasks/Retrieval/law/LegalQuADRetrieval.py
-
Update scripts/run_mteb_law.py
-
Update mteb/tasks/Retrieval/law/LegalSummarizationRetrieval.py
-
Update mteb/tasks/Retrieval/law/LegalSummarizationRetrieval.py
-
Update mteb/tasks/Retrieval/law/LeCaRDv2Retrieval.py
-
Update mteb/tasks/Retrieval/law/LeCaRDv2Retrieval.py
-
Rename GerDaLIRRetrieval.py to GerDaLIRSmallRetrieval.py
-
Update mteb/tasks/Retrieval/init.py
-
Update GerDaLIRSmallRetrieval.py
Add metadata
- Update GerDaLIRSmallRetrieval.py
Update metadata
- Update AILACasedocsRetrieval.py
Update AILACasedocsRetrieval metadata
- Update AILAStatutesRetrieval.py
Update AILAStatutesRetrieval metadata
- Update LeCaRDv2Retrieval.py
Update LeCaRDv2Retrieval metadata
- Update LegalBenchConsumerContractsQARetrieval.py
Update LegalBenchConsumerContractsQARetrieval metadata
- Update LegalBenchCorporateLobbyingRetrieval.py
Update LegalBenchCorporateLobbyingRetrieval metadata
- Update LegalQuADRetrieval.py
Update LegalQuADRetrieval metadata
- Update LegalSummarizationRetrieval.py
Update LegalSummarizationRetrieval metadata
- Update AILACasedocsRetrieval.py
Update AILACasedocsRetrieval
- Update AILACasedocsRetrieval.py
Update AILACasedocsRetrieval metadata
- Update AILAStatutesRetrieval.py
Update AILAStatutesRetrieval metadata
- Update GerDaLIRSmallRetrieval.py
Update GerDaLIRSmallRetrieval metadata
- Update LeCaRDv2Retrieval.py
Update LeCaRDv2Retrieval metadata
-
Update LegalBenchConsumerContractsQARetrieval.py
-
Update LegalBenchCorporateLobbyingRetrieval.py
-
Update LegalQuADRetrieval.py
-
Update LegalSummarizationRetrieval.py
-
Update AILACasedocsRetrieval.py
-
Update AILAStatutesRetrieval.py
-
Update GerDaLIRSmallRetrieval.py
-
Update LeCaRDv2Retrieval.py
-
move dataset language folder
-
update order
Co-authored-by: Niklas Muennighoff <n.muennighoff@gmail.com> (6e3f419
)
1.5.2
1.5.1
1.5.1 (2024-04-03)
Fix
-
fix: Added tests for checking datasets (#307)
-
fix: Fixed hf_hub_name for WikiCitiesClustering
-
Added points for this PR and a 3 other minor dataset fixes
-
feat: Added tests which validated that datasets are available
-
fix: Updated hf references and revisions to multiple datasets
-
Added points for submission
-
fix: Added suggestions from the review
-
Apply suggestions from code review
Co-authored-by: Imene Kerboua <33312980+imenelydiaker@users.noreply.github.com>
-
fix: sped up async test for whether datasets exist
-
fix: Updated revisions
-
fix: reuploaded scandeval datasets
-
fix: Applied formatter
Co-authored-by: Imene Kerboua <33312980+imenelydiaker@users.noreply.github.com> (8d804f4
)
1.5.0
1.5.0 (2024-04-02)
Feature
-
feat: Allow extending the load_dataset parameters in custom tasks inheriting AbsTask (#299)
-
Allow extending the load_dataset parameters
-
format
-
Fix test
-
remove duplicated logic from AbsTask, now handled in the metadata
-
add tests
-
remove comments, moved to PR
-
format
-
extend metadata dict from super class
-
Remove additional load_data
-
test: adding very high level test
-
Remove hf_hub_name and add test
-
Fix revision in output file
Co-authored-by: gbmarc1 <marcantoine.belanger@shopify.com> (953780d
)