Sean Hughes

hughesthe1st's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

commented a paper 5 months ago

RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content

Paper • 2406.11811 • Published Jun 17 • 16 •

1

New activity in bigcode/starpii 7 months ago

Corrections to Performance number for RegEx to reflect data from StarCoder paper

#10 opened 7 months ago by hughesthe1st

New activity in bigcode/starcoder 9 months ago

Added clarifications about the model limitations, usage data, and content detection tools.

#104 opened 9 months ago by hughesthe1st

New activity in bigcode/governance-card over 1 year ago

Added link to May 4th announcement

#10 opened over 1 year ago by hughesthe1st

Updated link to Paper to reflect submission to arXiv

#9 opened over 1 year ago by hughesthe1st

polish, Santacoder emissions calculation

#8 opened over 1 year ago by sebpaquet

More info on data collection

#7 opened over 1 year ago by harmdevries

Changed from crowdsourcing to data annotation

#6 opened over 1 year ago by hughesthe1st

Added Toloka details

#5 opened over 1 year ago by hughesthe1st

Typo correction

#4 opened over 1 year ago by hughesthe1st

Typos

#3 opened over 1 year ago by hughesthe1st

Added note about this being a living document

#2 opened over 1 year ago by hughesthe1st

Edited for accuracy

#1 opened over 1 year ago by hughesthe1st

New activity in bigcode/the-stack about 2 years ago

Infographic image contains typo "licence" > "license"

1

#6 opened about 2 years ago by hughesthe1st