Autoencoding Transformers

DistilBERT is a small, fast, cheap and light Transformer model based on the BERT architecture. Knowledge distillation is performed during the pre-training phase to reduce the size of a BERT model by 40%. To leverage the inductive biases learned by larger models during pre-training, the authors introduce a triple loss combining language modeling, distillation and cosine-distance losses.

Source: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter


Paper Code Results Date Stars


Component Type
Language Models