architectures · microsoft
Dilated-attention transformer with near-linear scaling, demonstrated to 1B-token context windows (Ding et al., 2023).
| Weight file SHA-256 | dfc666458a07fb9ca9b6864e38ef6acb6c3642850926f4c7591b32679aef0294 |
|---|
| Publisher | microsoft |
|---|---|
| Origin | United States |
| Licence | MIT |
| Pulls recorded here | 9,101 |
Registry record as of 2026-06-06. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.