Mteb

Documentation

* docs: points (1057)

* points

* Update 980.jsonl ([`30f12ca`](https://github.com/embeddings-benchmark/mteb/commit/30f12caaef466447aab547f17ad9de57ece44875))

Fix

* fix: Update salesforce_models (1053)

Update salesforce_models.py ([`061c3e3`](https://github.com/embeddings-benchmark/mteb/commit/061c3e3e02e2769430678580bb72765b84670807))

Unknown

* Update points table ([`38552d5`](https://github.com/embeddings-benchmark/mteb/commit/38552d577db99501e5a7e89c584d6431e7df8755))

* Fix query format (1042)

* Fix query format

* format ([`8adcaa0`](https://github.com/embeddings-benchmark/mteb/commit/8adcaa01d6021d54817ca5343cb69c9b77accdc9))

Fix

* fix: update __init__ in the classfication task for the swalihiNewsClassfication model to be seen (1044)

* swahili_news_classfication

* update_two

* Update Swahili addin source and refeence

* Update SwahiliNewsClassification.py

* Update SwahiliNewsClassification.py

* addition info about group

* remove unnecessary line

* Create __init__.py

* update __init__.py

This update __init__ in the classification tasks is to enable it to be seen by the tasks calling.

from .swa.SwahiliNewsClassification import *

* Upate with new test and lint ([`0822cd6`](https://github.com/embeddings-benchmark/mteb/commit/0822cd676a6f4f8f6e40a8cee6f9bcba10410afa))

Unknown

* Update tasks table ([`265e861`](https://github.com/embeddings-benchmark/mteb/commit/265e86185899aeeee087615b1a30c6a9d1cc2893))

Fix

* fix: Added Missing Models (1014)

* Added utility function for downloading models results

* Added result tables

* Added missing models

* fix: Fixed subset warning for later versions of polars

* Update scripts/mmteb/running_model/check_results.py

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

* removed used code segment

* format

---------

Co-authored-by: Niklas Muennighoff <n.muennighoffgmail.com> ([`602f4c0`](https://github.com/embeddings-benchmark/mteb/commit/602f4c0c6c39dde976604d057844d5e1d2e3c5bb))

Fix

* fix: Added encode_kwargs as the input for encode arguments and added batch_size to CLI (1030)

* ci: fix outdated CI for pandas

* fix: Added encode_kwargs as the input for encode arguments and added batch_size to CLI

This PR adds encode_kwargs as an argument to MTEB.run(..., encode_kwargs) which allows passing in arguments to model.encode calls. This has the benefit of removing/distinguishing between multiple model arguments present in the code.

Where default were already in place I have replaced kept them, future PRs might standardize or remove these.

I also add a test to ensure that the encode_kwargs in all cases are passed to the model.encode.

I additionally also add the batch_size argument to the CLI.

* add batch size in for backward compat.

* fixed misspecified defaults

* format

* Added in example of encode_kwargs

* Update mteb/abstasks/AbsTask.py

Co-authored-by: Isaac Chung <chungisaac1217gmail.com>

* Update README.md

Co-authored-by: Isaac Chung <chungisaac1217gmail.com>

---------

Co-authored-by: Isaac Chung <chungisaac1217gmail.com> ([`9032f02`](https://github.com/embeddings-benchmark/mteb/commit/9032f02b56fb0ee6aa43f2cfbfa3a2125ac13c2b))

Fix

* fix: change e5 default to use cuda if available (1033) ([`91400d3`](https://github.com/embeddings-benchmark/mteb/commit/91400d36a794facc1c8ed703617d2b3ea034a40b))

Ci

* ci: fix docs ci again (1031) ([`2daeeb9`](https://github.com/embeddings-benchmark/mteb/commit/2daeeb977ba5262d273f1b43caee97bae940215c))

Fix

* fix: minor update __init__ was not included make the repo not being able to be called as the module (1032)

* swahili_news_classfication

* update_two

* Update Swahili addin source and refeence

* Update SwahiliNewsClassification.py

* Update SwahiliNewsClassification.py

* addition info about group

* remove unnecessary line

* Create __init__.py ([`593d349`](https://github.com/embeddings-benchmark/mteb/commit/593d349b05030458983cf18ed87a9564f7b20f47))

Unknown

* Update tasks table ([`403dcdb`](https://github.com/embeddings-benchmark/mteb/commit/403dcdbbbb50ad67aadd3c0cff2d20cb4c957860))