Releases: KennethEnevoldsen/scandinavian-embedding-benchmark
v0.13.8
v0.13.8 (2024-12-26)
Ci
-
ci: update docs ci for UV (
f69313f
) -
ci: update docs ci for UV (
0c99b3b
) -
ci: fix remaining ci (
6459ea1
) -
ci: Update ci to work with uv (
46c4af6
) -
ci: Update ci to use UV (
b59f6e9
)
Fix
- fix: update uv (
a18205c
)
Unknown
- Merge pull request #189 from KennethEnevoldsen/add-jina
fix: re-add jina and add arctic (61d3255
)
-
Merge branch 'add-jina' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into add-jina (
77a7362
) -
format (
af596d5
) -
updated uv file (
d6298dd
) -
Merge branch 'main' into add-jina (
e898adf
) -
finally got batching to work correcrtly (
ff8d2db
) -
add results (
3a8ecfa
) -
convert makefile to uv (
9c9e7c6
) -
Merge branch 'add-jina' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into add-jina (
60cc806
) -
Update makefile (
5128f41
) -
Merge pull request #184 from KennethEnevoldsen/historical_task
fix: Historical task (17e35a0
)
-
Added results for jina (
ba4e15d
) -
fixed bugs revealed by type checker (
c226638
) -
fixed ruff (
acbaa3f
) -
fix import (
f521344
) -
Merge branch 'main' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into historical_task (
e813b35
) -
Added jina results (
c986df4
) -
added arctic model (
9d87597
) -
added results (
b597013
) -
Merge branch 'add-jina' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into add-jina (
2222d52
) -
delete all prev scores
with the exception of LCC which have been overwritten with new scores (369fb76
)
-
added a few fixes to the jina implementation (
a496071
) -
Merge branch 'add-jina' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into add-jina (
83af9cb
) -
Merge branch 'main' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into add-jina (
ccb84b1
)
v0.13.7
v0.13.7 (2024-11-14)
Fix
-
fix: Add Jina
-
fix: Add Jina
I am still running the model
-
Add results for Jina
-
Add results for Jina
-
format fixes
-
Update mkdocs to legacy python
Co-authored-by: Your Name <[email protected]> (84c2f91
)
v0.13.6
v0.13.6 (2024-07-23)
Documentation
- docs: fix sizes of tables (
07a7ec3
)
Fix
- fix: Added language to KFST (
c89856a
)
Unknown
- Merge pull request #182 from KennethEnevoldsen/add_kfst_model
fix: Added language to KFST (324dde4
)
- Merge pull request #180 from KennethEnevoldsen/add_kfst_model
docs: fix sizes of tables (e8848e2
)
- Merge pull request #179 from KennethEnevoldsen/add_kfst_model
Added kfst model (542511d
)
- Added kfst model (
88dce65
)
v0.13.5
v0.13.5 (2024-07-19)
Ci
- ci: remove macos due to it being slow (
452bfe2
)
Documentation
Fix
-
fix: Added results from bge-m3 (
3703bac
) -
fix: type checking ignore voyage (
cd1da36
) -
fix: format (
b77caf9
) -
fix: Added models results for voyage (
fc19796
) -
fix: Added models results for newly added models (
2b0cba5
) -
fix: Added new models (
ea830fd
)
Unknown
- Merge pull request #178 from KennethEnevoldsen/add-models-and-muni-code
fix: Added bge, voyage, cmlm-multilingual and mxbai models (3e600a3
)
-
fix typeerrror (
43da9ca
) -
format (
e695520
) -
Merge branch 'add-models-and-muni-code' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into add-models-and-muni-code (
e3c1d89
) -
Aded bge results (
41e6904
) -
minor fixes (
ec0df26
) -
minor fixes (
d14d6a9
) -
Added speed estimates (
74323ee
) -
Merge branch 'add-models-and-muni-code' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into add-models-and-muni-code (
8f523f1
) -
Added MuniIntent classification (
274d7fa
) -
Update README.md (
920241c
) -
Update README.md (
5cff1b2
) -
Update citation.cff (
84360d4
) -
Merge pull request #175 from KennethEnevoldsen/add-licenses
docs: Added licenses (c8376f9
)
v0.13.4
v0.13.3
v0.13.3 (2024-02-23)
Documentation
- docs: Updated tables to include task subtypes (
e119c58
)
Fix
- fix: Added task subtypes to tasks
This follows the denotion in the paper. A task can have multiple task subtypes but only one task type. (7fc9ed5
)
Unknown
- Merge pull request #162 from KennethEnevoldsen/add-task-subtypes
Added task subtypes (363ab09
)
v0.13.2
v0.13.2 (2024-02-19)
Fix
- fix: Pass the task for encode_queries, and encode_corpus
This yield notable performance improvements for the instruct models for retrieval tasks (9992e80
)
Unknown
- Merge pull request #156 from KennethEnevoldsen/fix_instruct_tuned_embed
fix: Pass the task for encode_queries, and encode_corpus (13786fe
)
- Merge branch 'main' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into fix_instruct_tuned_embed (
69b2ae2
)
v0.13.1
v0.13.1 (2024-02-19)
Chore
- chore: remove test file (
14f9935
)
Documentation
- docs: Updte docs script to handle new name format (
aa171dd
)
Fix
-
fix: fix incorrect emb. size for e5 large instruct (
7865ad7
) -
fix: Added final for mult. e5 instruct, including speed test of ref. system (
08e1779
) -
fix: added multilingual-e5-large-instruct (
56bfc16
) -
fix: rename model_architecture to architecture to not take up protected attribute for pydantic (
f845a49
)
Unknown
- Merge pull request #155 from KennethEnevoldsen/add-multilingual-instruct
Add multilingual e5 instruct (c2cca49
)
v0.13.0
v0.13.0 (2024-02-19)
Feature
- feat: Ensure that all model names are consistent
i.e. that they have the same name as they would have on the benchmark (c2299cd
)
Fix
-
fix: made the to method optional on the encoder (
157a91c
) -
fix: Add to method to lazyloadencoder (
0b6d0be
) -
fix: Ensure return type is always np.ndarray (
e8d3994
) -
fix: Ensure return type is always np.ndarray (
06c5cd8
)
Unknown
- Merge pull request #153 from KennethEnevoldsen/ensure-consistent-names
Ensure consistent names (83fd962
)
- Merge branch 'ensure_return_type' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into ensure_return_type (
7d09487
)
v0.12.2
v0.12.2 (2024-02-17)
Ci
- ci: Added not planned as valid no stale label (
a2dd834
)
Fix
-
fix: Removed translate-embed integration test (
adb9cd6
) -
fix: removing smaller translate then embed models (
fbb9e97
) -
fix: removing smaller translate then embed models (
91f6b79
) -
fix: Add missing scores (
3b92090
) -
fix: Added e5 mistral scores (
7515e79
)
Style
- style: ran linting (
f729288
)
Unknown
- Merge pull request #143 from KennethEnevoldsen/run-e5
Updated e5-mistral model (0026c9c
)
-
Merge branch 'run-e5' of https://github.com/KennethEnevoldsen/scandinavian-embedding-benchmark into run-e5 (
fdc19fb
) -
Merge branch 'run-e5' of https://github.com/KennethEnevoldsen/Scandinavian-Embedding-Benchmark into run-e5 (
e691448
)