Skip to content

Releases: embeddings-benchmark/mteb

1.19.0

06 Nov 13:23
Compare
Choose a tag to compare

1.19.0 (2024-11-06)

Feature

  • feat: Standardize descriptive stats (#1375)

  • init

  • mock tests

  • remove debug prints

  • remove descriptive stats and move to n_samples

  • fix typo

  • fix create task table

  • fix citations

  • remove n_samples

  • metadata per task

  • add test

  • reformat task table

  • add n_samples property

  • fix tests

  • rename total_symbols to number_of_characters

  • Update mteb/abstasks/AbsTaskRetrieval.py

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com>

  • rename in tests

  • lint


Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com> (2854fa2)

Unknown

1.18.9

06 Nov 10:41
Compare
Choose a tag to compare

1.18.9 (2024-11-06)

Fix

  • fix: Disable rich output with verbosity=0 on evaluation.run (#1395)

  • feat: verbose=0 now supress rich console output

  • fix: removed unnecesary list comprenhension (1bb1ca3)

1.18.8

04 Nov 23:37
Compare
Choose a tag to compare

1.18.8 (2024-11-04)

Fix

  • fix: Update logging verbosity levels in MTEB (#1384)

  • Fix verbosity handling in MTEB.py for consistent logging

  • updates

  • update docstrings

  • linting code (35daf58)

1.18.7

04 Nov 14:14
Compare
Choose a tag to compare

1.18.7 (2024-11-04)

Fix

  • fix: Leaderboard UI improvements (#1370)

  • Added elementary search bar with RegEx functionality

  • Improved layout

  • Table improvements, adjusted column width and added links

  • Update benchmark filter description

Co-authored-by: Isaac Chung <chungisaac1217@gmail.com>

  • Added instructions on multiple search queries

Co-authored-by: Isaac Chung <chungisaac1217@gmail.com>


Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> (92fe9cb)

1.18.6

31 Oct 08:33
Compare
Choose a tag to compare

1.18.6 (2024-10-31)

Fix

  • fix: Integrate prompts to task metadata (#1300)

  • init

  • add DatasetDict

  • add classification

  • add clustering

  • add pair classification

  • add retrieval

  • add all prompts

  • start integrating prompts

  • refactor instruct models

  • lint

  • fix test

  • fix

  • fix no prompt in prompt dict

  • add more logging

  • add more logging

  • Apply suggestions from code review

Co-authored-by: Isaac Chung <chungisaac1217@gmail.com>

  • fix code review

  • fix use_instructions

  • add log if instruction template not set

  • fix metadata

  • lint

  • fix brazilian

  • remove MetadataDatasetDict

  • rollback test metadata


Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> (029d378)

1.18.5

31 Oct 07:35
Compare
Choose a tag to compare

1.18.5 (2024-10-31)

Fix

  • fix: Speed up leaderboard by caching and skipping validation (#1365)

  • Made loading and filtering faster by removing unnecessary validation

  • Made select_tasks faster by removing validation

  • Added caching to leaderboard

  • Ran linting

  • Added missing future import (f1bc375)

1.18.4

30 Oct 19:59
Compare
Choose a tag to compare

1.18.4 (2024-10-30)

Fix

  • fix: make sure test is the default split for FEVER (#1361)

The other splits can still be run as long as they are specified. (d9626ab)

1.18.3

30 Oct 14:24
Compare
Choose a tag to compare

1.18.3 (2024-10-30)

Fix

  • fix: Update KorSarcasm to avoid trust-remote code (#1364) (756ba7e)

Unknown

  • Leaderboard updates: Model meta + task and benchmark info (#1345)

  • Added benchmark description and citation to leaderboard

  • Added model information to main table

  • Fixed citation box

  • Added table tab with task information

  • Added button for benchmark link if specified

  • Formatted model column in per_task table properly

  • Implemented model filtering based on metadata

  • Fixed maximum minimum model sizes

  • Ran linting

  • Replaced mean rank with borda rank in main table (298b0bd)

1.18.2

30 Oct 09:51
Compare
Choose a tag to compare

1.18.2 (2024-10-30)

Fix

  • fix: upload BrazilianToxicTweetsClassification to hf (#1352)

upload to hf (9c7a1c2)

1.18.1

30 Oct 09:08
Compare
Choose a tag to compare

1.18.1 (2024-10-30)

Fix

  • fix: Add jina, uae, stella models (#1319)

  • add models

  • fix

  • fix

  • fix prompt

  • Update mteb/models/jina_models.py

Co-authored-by: Wang Bo <bo.wang@jina.ai>

  • Update mteb/models/jina_models.py

Co-authored-by: Wang Bo <bo.wang@jina.ai>

  • try reeval stella

  • change to e5

  • change to e5

  • add metadata

  • update languages

  • Update mteb/models/jina_models.py

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com>

  • remove docstring

  • remove trust remote

  • update model meta

  • Set minimal version


Co-authored-by: Wang Bo <bo.wang@jina.ai>
Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com> (0b846ff)

  • fix: remove accidentally commited file (16a333e)