List your company

Language Modeling on FineWeb in-distribution

19.73Perplexity (PPL)SSA
19.644820.219920.79521.3701Aug 20, 2025

Evaluation results

MethodLinks
SSAModel Architecture=Nemotron-style decoder, Parameters=114M, Training Steps=22K, Training Dataset=FineWeb2025.0819.73
SoftmaxModel Architecture=Nemotron-style decoder, Parameters=114M, Training Steps=22K, Training Dataset=FineWeb2025.0821.86