MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
Paper
•
2402.14905
•
Published
•
126
MobileLLM
Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905
-
-
facebook/MobileLLM-125M
Text Generation • Updated • 10.6k • 87 -
facebook/MobileLLM-350M
Text Generation • Updated • 629 • 24 -
facebook/MobileLLM-600M
Text Generation • Updated • 1.22k • 27 -
facebook/MobileLLM-1B
Text Generation • Updated • 8.23k • 110 -
facebook/MobileLLM-1.5B
Text Generation • Updated • 55 • 2 -
facebook/MobileLLM-125M-layer-share
Text Generation • Updated • 238 • 1 -
facebook/MobileLLM-350M-layer-share
Text Generation • Updated • 157 • 4