sbordt/OLMo-2-1B-Exp
1B • Updated
• 8
train-once-answer-all
Modes and datasets for the paper "Train Once, Answer All: Many Pretraining Experiments for the Cost of One", ICLR 2026
-
-
sbordt/OLMo-2-1B-7x
1B • Updated • 1 -
sbordt/OLMo-2-1B-Exp-Dataset
Viewer • Updated • 5.51M • 20 -
sbordt/OLMo-2-546M-Exp
Text Generation • 0.5B • Updated • 1 -
sbordt/OLMo-2-179M-Exp
Text Generation • 0.2B • Updated • 1 -
sbordt/toaa_mathematical_reasoning
Viewer • Updated • 116k • 15 -
sbordt/OLMo-2-2.7B-Exp
Text Generation • 3B • Updated • 1