| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| ByT5: Towards a token-free future with pre-trained byte-to-byte models | ✓ Link | 83.7 | ByT5 XXL | 2021-05-28 |
| Rethinking embedding coupling in pre-trained language models | ✓ Link | 71.3 | Decoupled | 2020-10-24 |
| Rethinking embedding coupling in pre-trained language models | ✓ Link | 70.7 | Coupled | 2020-10-24 |
| ByT5: Towards a token-free future with pre-trained byte-to-byte models | ✓ Link | 69.1 | ByT5 Small | 2021-05-28 |
| mGPT: Few-Shot Learners Go Multilingual | ✓ Link | 40.6 | mGPT | 2022-04-15 |