Mteb

Fix

* fix: Add NusaParagraph Emotion Classification (928)

* add NusaTranslationEmotionClassification

* update name

* add new task

* add new task

* Update mteb/tasks/Classification/multilingual/NusaParagraphEmotionClassification.py

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com>

* add sizes

* add point

* add results

* update desc

---------

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com> ([`5e4ad44`](https://github.com/embeddings-benchmark/mteb/commit/5e4ad442535a20719f42457ca034269df3de3646))

* fix: Add NusaParagraph Topic Classification (927)

* add data

* update lang code

* update metadata

* update metadata

* update metadata

* update files

* Update mteb/tasks/Classification/multilingual/NusaParagraphTopicClassification.py

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com>

* update avg char

* add points

* add results and fix lint

---------

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com> ([`e13f037`](https://github.com/embeddings-benchmark/mteb/commit/e13f0371341dd08b7868f5e049478dae891a27a5))

* fix: Add NollySenti Bitext Mining (MINERS) (915)

* add NollySentiBitextMining

* update reference

* update avg char

* add points

* add results ([`df68f8c`](https://github.com/embeddings-benchmark/mteb/commit/df68f8c7aadbee9b09da4193b9d6badc3990a97b))

Unknown

* Update tasks table ([`bf7fc5b`](https://github.com/embeddings-benchmark/mteb/commit/bf7fc5b72ef1d09fa5dcd5445bbc617e13e04e13))

* Update points table ([`19cc06f`](https://github.com/embeddings-benchmark/mteb/commit/19cc06ffbea0d732e936ff4431d66fd6004efbb4))

* Update tasks table ([`0f51819`](https://github.com/embeddings-benchmark/mteb/commit/0f5181945db20410e9d1f3af3be2060b411aadb4))

* Update points table ([`4a8bfd2`](https://github.com/embeddings-benchmark/mteb/commit/4a8bfd2cd9b1acc2d14bf4a45b84719d57104330))

* Update points table ([`2a31c8c`](https://github.com/embeddings-benchmark/mteb/commit/2a31c8c6f1e21fe5f91e794a313f1cd3083beff3))

Fix

* fix: Add NusaTranslation Bitext Mining (MINERS) (914)

* add NusaTranslationBitextMining

* fix lint

* update dataset nameg

* update language code

* update avg len

* add points

* add results and fix lint ([`78f34ad`](https://github.com/embeddings-benchmark/mteb/commit/78f34ad33841ee1a15073cee8a5af1d7e881c67d))

* fix: Add NusaX Bitext Mining (MINERS) (910)

* add init and dataset

* update metadata

* update bibtex

* update metadata

* update avg character length

* update dataset nameg

* add instruction

* revert instructions

* fix lint

* update avg char length

* add points

* update points ([`25c7606`](https://github.com/embeddings-benchmark/mteb/commit/25c76061db029f4dd65e4542a1199b2f460b34ab))

Unknown

* Update tasks table ([`83ccaa1`](https://github.com/embeddings-benchmark/mteb/commit/83ccaa1f684f0411bdb6084da371e3838d87a389))

* Update points table ([`12d5272`](https://github.com/embeddings-benchmark/mteb/commit/12d5272c39e9ed2434af9fb46494ff6cb1c63b9e))

* Update tasks table ([`a21310a`](https://github.com/embeddings-benchmark/mteb/commit/a21310addacd1ef2c1088087a4e1696bc13b7a3b))

* Update points table ([`a26bb6a`](https://github.com/embeddings-benchmark/mteb/commit/a26bb6a6ed4b843b080ad62e890a86120ead1df1))

Documentation

* docs: added documentation for wiki clustering (934)

docs: added documentatio for wiki clustering ([`8e39cfb`](https://github.com/embeddings-benchmark/mteb/commit/8e39cfb036a922d3f457eeb898b9d0e3857a9d21))

Fix

* fix: Add STS dataset SemRel2024 (917)

* Add STS dataset: SemRel2024

* Add results for STS task SemRel24

* Add points

* Update mteb/tasks/STS/multilingual/SemRel24STS.py

* Update review points

---------

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com> ([`319ed83`](https://github.com/embeddings-benchmark/mteb/commit/319ed833ae744cfc1006060638324a7c3fe67256))

Unknown

* Update tasks table ([`dab4aff`](https://github.com/embeddings-benchmark/mteb/commit/dab4aff2c15744635acade8c12e04660c42dd551))

* Update points table ([`8ce9771`](https://github.com/embeddings-benchmark/mteb/commit/8ce97713090ad43e0cd67a1d2574dd4931b46207))

Fix

* fix: Update annotations for multilingual classification tasks (923)

* Update MTOPIntentClassification.py

* Update MTOPDomainClassification.py

* Update MassiveIntentClassification.py

* Update MassiveScenarioClassification.py

* Update MassiveScenarioClassification.py

* Update MassiveIntentClassification.py

* add points

---------

Co-authored-by: Tikhonova Maria <m_tikhonova94mail.ru> ([`568651b`](https://github.com/embeddings-benchmark/mteb/commit/568651bab6dd57ae8fc2216d5e192da351f44a98))

Unknown

* Update tasks table ([`42d4ecd`](https://github.com/embeddings-benchmark/mteb/commit/42d4ecd63d50301ea0f094e3189457fb18cd6c39))

* Update points table ([`53fb2f8`](https://github.com/embeddings-benchmark/mteb/commit/53fb2f8ed6de90b1d2a9a2e8723771aaefcfaede))

Fix

* fix: Added the ability to make task specific instructions, tested using e5 instruct (888)

* Added prompting along with e5 instruct

All encode calls now include a prompt_name (following the variable name in sentence transformer&39;s encode), which provided the task name. The model can then use a custom prompt pr. task if they wish (or encode based on e.g. task type).

Additionally to test it out I have also added the two e5 instruct models.

* format

* updated based on review

* format

* Update mteb/models/instructions.py

Co-authored-by: Niklas Muennighoff <n.muennighoffgmail.com>

* Update mteb/models/__init__.py

Co-authored-by: Niklas Muennighoff <n.muennighoffgmail.com>

* Added additional tests for instructions

---------

Co-authored-by: Niklas Muennighoff <n.muennighoffgmail.com> ([`40208cf`](https://github.com/embeddings-benchmark/mteb/commit/40208cfaf0bf588515e3a077b4d7e5fc5fa98200))

Unknown

* Update points table ([`b97ad77`](https://github.com/embeddings-benchmark/mteb/commit/b97ad779c3eac25d9ac8098bf84300197964666f))

Fix

* fix: Fix create_meta function in cli.py (912)

* Update cli.py

Fix create_meta function

* Update test files ([`af365b7`](https://github.com/embeddings-benchmark/mteb/commit/af365b795e2c54b25b0e02bbb0788ba9d3c403c7))

Unknown

* format ([`c47d279`](https://github.com/embeddings-benchmark/mteb/commit/c47d2795b4297792aa55f059b833055a4a13106c))

* Fix GritLM Loading (925)

* add gritlm to init file

* sort

---------

Co-authored-by: Niklas Muennighoff <n.muennighoffgmail.com> ([`55fb52e`](https://github.com/embeddings-benchmark/mteb/commit/55fb52e514109aef8a8077bf88ffd16c950eb4c2))