Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implemented EU22/EU5 translations #105

Open
wants to merge 13 commits into
base: master
Choose a base branch
from
Open

Conversation

jjbuschhoff
Copy link

Added translated datasets for arc, truthfulqa, gsm8k, hellaswag and mmlu.

@KlaudiaTH KlaudiaTH self-assigned this Jan 12, 2024
Copy link
Collaborator

@KlaudiaTH KlaudiaTH left a comment

Choose a reason for hiding this comment

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

Some of the tasks are not translated into all 20 EU languages available on DeepL, but only to DE/FR/IT/ES.
Currently the tasks are being run on the cluster. If there should occur problems, I'll give an update.

lm_eval/tasks/opengptx/all_tasks_registry.py Outdated Show resolved Hide resolved
lm_eval/tasks/opengptx/arcx.py Outdated Show resolved Hide resolved
lm_eval/tasks/opengptx/arcx.py Show resolved Hide resolved
lm_eval/tasks/opengptx/arcx.py Outdated Show resolved Hide resolved
super().__init__()

def has_training_docs(self):
return False
Copy link
Collaborator

Choose a reason for hiding this comment

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

Looking at https://huggingface.co/datasets/openGPT-X/mmlux/tree/main, there seem to be three splits per subject (dev, validation, test) - should dev be used as train split?

lm_eval/tasks/opengptx/truthfulqax.py Outdated Show resolved Hide resolved
volume={abs/1803.05457}
}
"""
LANGS = [
Copy link
Collaborator

Choose a reason for hiding this comment

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

Would it make sense to include English here to ensure that all languages are evaluated the same way?

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