Skip to content

Conversation

Samoed
Copy link
Member

@Samoed Samoed commented May 3, 2025

  • Fixed loading for some tasks BEIR-NL and updated trust_remote_code for some legal tasks.
  • Support PairClassification with old format
  • Added flag for reuploading to add link to source dataset when reuploading
  • I've noticed that I'm uploading retrieval qrels to qrels split instead of default. So I've added to dataset loader support qrels too
  • Fixed code language mapping in HF card
  • Fixed loading of long split of BrightRetrieval

@Samoed Samoed changed the title fix retrieval dataset upload reupload datasets May 6, 2025
Samoed added 2 commits June 18, 2025 22:17
# Conflicts:
#	mteb/abstasks/AbsTask.py
#	mteb/abstasks/dataset_card_template.md
# Conflicts:
#	mteb/tasks/PairClassification/deu/FalseFriendsDeEnPC.py
#	mteb/tasks/Retrieval/vie/VieQuADRetrieval.py
#	mteb/tasks/STS/kor/KlueSTS.py
@Samoed Samoed marked this pull request as ready for review June 25, 2025 21:42
@Samoed Samoed requested a review from KennethEnevoldsen June 25, 2025 21:42
Copy link
Contributor

@KennethEnevoldsen KennethEnevoldsen left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@Samoed seems like some test fail and like this PR is missing a description - will you take a look at these before I review?

@Samoed Samoed requested a review from KennethEnevoldsen July 5, 2025 15:15
Copy link
Contributor

@KennethEnevoldsen KennethEnevoldsen left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Generally looks good - only a few minor things

@Samoed Samoed merged commit ba7bb7d into v2.0.0 Jul 20, 2025
8 checks passed
@Samoed Samoed deleted the upload_datasets branch July 20, 2025 10:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants