Methods › Natural Language Processing › Autoencoding Transformers › TernaryBERT
TernaryBERT
Introduced by Wei Zhang et al. in TernaryBERT: Distillation-aware Ultra-low Bit BERT
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
TernaryBERT is a Transformer-based model which ternarizes the weights of a pretrained BERT model to {-1,0,+1}, with different granularities for word embedding and weights in the Transformer layer. Instead of directly using knowledge distillation to compress a model, it is used to improve the performance of ternarized student model with the same size as the teacher model. In this way, we transfer the knowledge from the highly-accurate teacher model to the ternarized student model with smaller capacity.
Papers archive 2025-07-28
2 shown of 2, 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.
-
BinaryBERT: Pushing the Limit of BERT Quantization 31 Dec 2020 · 1 repository · arXiv:2012.15701Syntology ran 4 of 6 samples · 2 unverified · 6 pointer-only (licence)
-
TernaryBERT: Distillation-aware Ultra-low Bit BERT 27 Sep 2020 · 5 repositories · arXiv:2009.12812
Tasks archive 2025-07-28
4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Quantization | 2 |
| Binarization | 1 |
| Knowledge Distillation | 1 |
| Model Compression | 1 |
Usage over time archive 2025-07-28
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
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