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 lighterPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Text Classification | 18 | 7.47% |
Sentiment Analysis | 18 | 7.47% |
Language Modelling | 17 | 7.05% |
Classification | 16 | 6.64% |
Question Answering | 12 | 4.98% |
Sentence | 9 | 3.73% |
Quantization | 7 | 2.90% |
Natural Language Understanding | 6 | 2.49% |
Model Compression | 6 | 2.49% |