A Deepdive into Aya Expanse: Advancing the Frontier of Multilinguality
•
60
Shivalika Singh
shivi
AI & ML interests
None yet
Recent Activity
reacted
to
dvilasuero's
post
with ❤️
3 days ago
🌐 Announcing Global-MMLU: an improved MMLU Open dataset with evaluation coverage across 42 languages, built with Argilla and the Hugging Face community.
Global-MMLU is the result of months of work with the goal of advancing Multilingual LLM evaluation. It's been an amazing open science effort with collaborators from Cohere For AI, Mila - Quebec Artificial Intelligence Institute, EPFL, Massachusetts Institute of Technology, AI Singapore, National University of Singapore, KAIST, Instituto Superior Técnico, Carnegie Mellon University, CONICET, and University of Buenos Aires.
🏷️ +200 contributors used Argilla MMLU questions where regional, dialect, or cultural knowledge was required to answer correctly. 85% of the questions required Western-centric knowledge!
Thanks to this annotation process, the open dataset contains two subsets:
1. 🗽 Culturally Agnostic: no specific regional, cultural knowledge is required.
2. ⚖️ Culturally Sensitive: requires dialect, cultural knowledge or geographic knowledge to answer correctly.
Moreover, we provide high quality translations of 25 out of 42 languages, thanks again to the community and professional annotators leveraging Argilla on the Hub.
I hope this will ensure a better understanding of the limitations and challenges for making open AI useful for many languages.
Dataset: https://huggingface.co./datasets/CohereForAI/Global-MMLU
reacted
to
dvilasuero's
post
with 🔥
3 days ago
🌐 Announcing Global-MMLU: an improved MMLU Open dataset with evaluation coverage across 42 languages, built with Argilla and the Hugging Face community.
Global-MMLU is the result of months of work with the goal of advancing Multilingual LLM evaluation. It's been an amazing open science effort with collaborators from Cohere For AI, Mila - Quebec Artificial Intelligence Institute, EPFL, Massachusetts Institute of Technology, AI Singapore, National University of Singapore, KAIST, Instituto Superior Técnico, Carnegie Mellon University, CONICET, and University of Buenos Aires.
🏷️ +200 contributors used Argilla MMLU questions where regional, dialect, or cultural knowledge was required to answer correctly. 85% of the questions required Western-centric knowledge!
Thanks to this annotation process, the open dataset contains two subsets:
1. 🗽 Culturally Agnostic: no specific regional, cultural knowledge is required.
2. ⚖️ Culturally Sensitive: requires dialect, cultural knowledge or geographic knowledge to answer correctly.
Moreover, we provide high quality translations of 25 out of 42 languages, thanks again to the community and professional annotators leveraging Argilla on the Hub.
I hope this will ensure a better understanding of the limitations and challenges for making open AI useful for many languages.
Dataset: https://huggingface.co./datasets/CohereForAI/Global-MMLU
updated
a dataset
5 days ago
CohereForAI/Global-MMLU-Lite
Articles
Organizations
spaces
4
models
19
shivi/stable-diffusion-3-medium-diffusers
Text-to-Image
•
Updated
shivi/roberta-large-peft-lora-v2
Updated
shivi/roberta-large-peft-lora
Updated
shivi/xlm-roberta-base-finetuned-panx-de
Token Classification
•
Updated
•
18
shivi/distilbert-base-uncased-finetuned-movie-genre
Text Classification
•
Updated
•
14
shivi/distilbert-base-uncased-finetuned-emotion
Text Classification
•
Updated
•
15
shivi/video-mask2former-swin-tiny-youtubevis-2021-instance
Image Segmentation
•
Updated
•
11
•
2
shivi/video-mask2former-swin-small-youtubevis-2021-instance
Image Segmentation
•
Updated
•
17
shivi/video-mask2former-swin-large-youtubevis-2021-instance
Image Segmentation
•
Updated
•
27
shivi/video-mask2former-swin-base-IN21k-youtubevis-2021-instance
Image Segmentation
•
Updated
•
13