#BertGoBrrrt

Exponentially Faster Language Modelling Language models only really need to use an exponential fraction of their neurons for individual inferences. As proof, we present UltraFastBERT, a BERT variant that uses 0.3% of its neurons during...

UltraFastBERT, a BERT model using only 0.3% of its neurons for inference, matching the performance of standard BERT models. Achieving up to 78x speedup over traditional methods. #NLP #LLMs #BertGoBrrrt