Skip to content

1.31.4

Compare
Choose a tag to compare
@KennethEnevoldsen KennethEnevoldsen released this 29 Jan 11:29
· 147 commits to main since this release

1.31.4 (2025-01-29)

Fix

  • fix: Allow aggregated tasks within benchmarks (#1771)

  • fix: Allow aggregated tasks within benchmarks

Fixes #1231

  • feat: Update task filtering, fixing bug on MTEB
  • Updated task filtering adding exclusive_language_filter and hf_subset
  • fix bug in MTEB where cross-lingual splits were included
  • added missing language filtering to MTEB(europe, beta) and MTEB(indic, beta)

The following code outlines the problems:

import mteb
from mteb.benchmarks import MTEB_ENG_CLASSIC

task = [t for t in MTEB_ENG_CLASSIC.tasks if t.metadata.name == "STS22"][0]
# was eq. to:
task = mteb.get_task("STS22", languages=["eng"])
task.hf_subsets
# correct filtering to English datasets:
# ['en', 'de-en', 'es-en', 'pl-en', 'zh-en']
# However it should be:
# ['en']

# with the changes it is:
task = [t for t in MTEB_ENG_CLASSIC.tasks if t.metadata.name == "STS22"][0]
task.hf_subsets
# ['en']
# eq. to
task = mteb.get_task("STS22", hf_subsets=["en"])
# which you can also obtain using the exclusive_language_filter (though not if there was multiple english splits):
task = mteb.get_task("STS22", languages=["eng"], exclusive_language_filter=True)
  • format

  • remove "en-ext" from AmazonCounterfactualClassification

  • fixed mteb(deu)

  • fix: simplify in a few areas

  • wip

  • tmp

  • sav

  • Allow aggregated tasks within benchmarks
    Fixes #1231

  • ensure correct formatting of eval_langs

  • ignore aggregate dataset

  • clean up dummy cases

  • add to mteb(eng, classic)

  • format

  • clean up

  • Allow aggregated tasks within benchmarks
    Fixes #1231

  • added fixed from comments

  • fix merge

  • format

  • Updated task type

  • Added minor fix for dummy tasks (8fb59a4)

Unknown