List your company

Language Modeling on OpenWebText (test val)

19.6PerplexityH3 Hybrid
19.38820.81922.2523.681Dec 28, 2022

Evaluation results

MethodLinks
H3 HybridNumber of Layers=12, Model Size=125M, Training Tokens=50B, Number of Attention Layers=22022.1219.6
GSS HybridNumber of Layers=12, Model Size=125M, Training Tokens=50B, Number of Attention Layers=22022.1219.8
TransformerNumber of Layers=12, Model Size=125M, Training Tokens=50B2022.1220.6
H3Number of Layers=12, Model Size=125M, Training Tokens=50B2022.1221
GSSNumber of Layers=12, Model Size=125M, Training Tokens=50B2022.1224
S4DNumber of Layers=12, Model Size=125M, Training Tokens=50B2022.1224.9