Repository navigation
Conversation
wgu9
force-pushed
the
fix-belebele-retrieval-config-loading
branch
from
June 29, 2026 19:17
8da5ea7 to
d0b2c5d
Compare
Contributor
Author
|
CI note: the current failing checks appear to be Hugging Face Hub availability/rate-limit issues rather than failures from this change.
The same PR already had |
Samoed
approved these changes
Jun 30, 2026
Samoed
approved these changes
Jun 30, 2026
Samoed
left a comment
Samoed
left a comment
Member
There was a problem hiding this comment.
I run and compared with original version from facebook/belebele and got same scores on random model
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes #4865.
BelebeleRetrievalstill attempted to loadmteb/belebelewithout a config and then index language configs from the returned object. The migrated Hugging Face dataset requires an explicit language config such aseng_Latn, so the task failed duringload_data()withValueError: Config name is missing.This PR loads only the language configs needed by the selected
hf_subsets, caches each language once, and keeps the existing query/corpus/qrels construction unchanged.Test Plan
uv run --group test pytest -q tests/test_tasks/test_load_data.pyuv run --group lint ruff check mteb/tasks/retrieval/multilingual/belebele_retrieval.py tests/test_tasks/test_load_data.pyuv run --group lint ruff format --check mteb/tasks/retrieval/multilingual/belebele_retrieval.py tests/test_tasks/test_load_data.pymteb.get_task("BelebeleRetrieval", hf_subsets=["eng_Latn-eng_Latn"]).load_data()produced 900 queries, 488 corpus docs, and 900 qrels.