SuperBPE: Space Travel for Language Models
Paper
•
2503.13423
•
Published
•
10
SuperBPE
SuperBPE tokenizers and models trained with them
-
-
UW/OLMo2-8B-SuperBPE-t180k
Text Generation • Updated • 2k • 7 -
UW/OLMo2-11B-SuperBPE-t180k
Text Generation • Updated • 19 • 2 -
UW/OLMo2-8B-SuperBPE-t160k
Text Generation • Updated • 7 • 3 -
UW/OLMo2-8B-SuperBPE-t80k
Text Generation • Updated • 45 -
UW/OLMo2-8B-BPE
Text Generation • Updated • 40 -
5
SuperBPE Playground
📝Experiment with and compare different tokenizers
-
UW/olmo-mix-1124-subset-p99
Updated • 609