Methods › Natural Language Processing › Transformers › DistilBERT

DistilBERT

166 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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,...

Papers archive 2025-07-28

30 shown of 166, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 172 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Sentiment Analysis23
Text Classification22
Classification21
text-classification20
Language Modelling18
Language Modeling14
Question Answering14
Knowledge Distillation12
Data Augmentation9
Sentence9
Transfer Learning9
Quantization8
Model Compression7
General Classification6
Natural Language Understanding6
Sentiment Classification6
Word Embeddings6
model6
GPU5
Large Language Model5

Usage over time archive 2025-07-28

Papers per year tagged with DistilBERT: 2019 to 2025, peak 34 34 0 2019: 1 paper 2019 2020: 27 papers 2020 2021: 34 papers 2021 2022: 22 papers 2022 2023: 34 papers 2023 2024: 33 papers 2024 2025: 15 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (166 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Transformers

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections