Alon Albalak's picture

Alon Albalak

alon-albalak

·

https://alon-albalak.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper about 1 month ago

OpenThoughts: Data Recipes for Reasoning Models

authored a paper about 1 month ago

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

upvoted a paper about 1 month ago

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

View all activity

Organizations

Papers 14

arxiv:2506.05209

arxiv:2506.04178

arxiv:2502.17387

arxiv:2501.04682

models 5

alon-albalak/ODM_1Bparams_50Btokens_seqlen2048

Feature Extraction • 1.0B • Updated Oct 26, 2023 • 9

alon-albalak/ODM_1B_params_50B_tokens

Feature Extraction • 0.9B • Updated Oct 10, 2023 • 7

alon-albalak/xlm-roberta-large-xquad

Question Answering • 0.6B • Updated Jul 1, 2023 • 18 • 2

alon-albalak/bert-base-multilingual-xquad

Question Answering • 0.2B • Updated Jul 1, 2023 • 13

alon-albalak/xlm-roberta-base-xquad

Question Answering • Updated Nov 5, 2021 • 13 • 2

datasets 0

None public yet